Vibe-Trading: Your Personal Trading Agent

HKUDS released Vibe-Trading, an open-source trading agent that executes trades via a single command, with updates including cross-platform setup, content-filter resilience, and Shadow Account conditional entry rules for precise trade signals.

English | 中文 /HKUDS/Vibe-Trading/blob/main/README zh.md | 日本語 /HKUDS/Vibe-Trading/blob/main/README ja.md | 한국어 /HKUDS/Vibe-Trading/blob/main/README ko.md | العربية /HKUDS/Vibe-Trading/blob/main/README ar.md One Command to Empower Your Agent with Comprehensive Trading Capabilities Website https://vibetrading.wiki/ · Docs https://vibetrading.wiki/docs/ · News -news · Features -key-features · Shadow Account -shadow-account · Demo -demo · Quick Start -quick-start · Examples -examples · API / MCP -api-server · Roadmap -roadmap · Contributing -contributing 2026-06-28 🧰 Cross-platform setup/dev + runtime and file-tool hardening : vibe-trading setup and vibe-trading dev now handle Windows TypeScript builds, launch the backend from the right cwd, use the Vite 5899 port, and shut child processes down cleanly 292 https://github.com/HKUDS/Vibe-Trading/pull/292 , thanks @digger-yu . Runtime status polling now degrades instead of crashing 322 https://github.com/HKUDS/Vibe-Trading/issues/322 ; MCP OAuth cache keys are sanitized 313 https://github.com/HKUDS/Vibe-Trading/issues/313 ; OpenAI defaults and Robinhood agent.json validation were tightened 319 https://github.com/HKUDS/Vibe-Trading/pull/319 , 320 https://github.com/HKUDS/Vibe-Trading/pull/320 , thanks @mvanhorn ; and file tools got isolated read/write roots plus broader sandbox tests 299 https://github.com/HKUDS/Vibe-Trading/pull/299 , thanks @skloxo . 2026-06-27 🧯 Content-filter resilience + Shadow Account feature contract cleanup : event-driven and swarm runs now skip individual LLM content-moderation hits, warn in run cards when filter rates are high, and recognize Gemini safety finish reasons instead of aborting an entire analysis 308 https://github.com/HKUDS/Vibe-Trading/pull/308 , closes 307 https://github.com/HKUDS/Vibe-Trading/issues/307 , thanks @shadowinlife . Shadow Account extraction/codegen now share one PRICE FEATURES contract and keep four-decimal return bounds, preventing rule/codegen drift and precision loss on prior 5d return 316 https://github.com/HKUDS/Vibe-Trading/pull/316 , thanks @Robin1987China . 2026-06-26 🎯 Shadow Account conditional entry + tushare ETF/index/HK routing : extracted Shadow Account rules now carry RSI / prior-return bounds, so the generated SignalEngine enters on real conditions RSI in range, prior-return in range instead of blindly replaying the holding cadence 314 https://github.com/HKUDS/Vibe-Trading/pull/314 , follows 302 https://github.com/HKUDS/Vibe-Trading/pull/302 , thanks @Robin1987China . The tushare loader also routes ETF/LOF → fund daily , indices → index daily , and HK equities → hk daily instead of always calling daily which silently returns empty for non-stocks , with per-symbol empty-result + partial-fetch warnings 315 https://github.com/HKUDS/Vibe-Trading/pull/315 , closes 310 https://github.com/HKUDS/Vibe-Trading/issues/310 , thanks @shadowinlife . Earlier news - 2026-06-25 🧪 Strict validation JSON + calmer agent context : standalone backtest validation now normalizes nested NaN / Infinity values before writing artifacts/validation.json or CLI stdout, so strict JSON parsers no longer choke on validation payloads 306 https://github.com/HKUDS/Vibe-Trading/pull/306 , thanks @gyx09212214-prog . The agent prompt also derives the current data-source count from the loader registry, and microcompact now waits for real token pressure instead of clearing older tool results during short runs 296 https://github.com/HKUDS/Vibe-Trading/pull/296 , closes 282 https://github.com/HKUDS/Vibe-Trading/issues/282 , thanks @MarkfuGod . - 2026-06-24 🎯 Shadow Account price context + reactive Chinese UI + LAN auth fix : Shadow Account rule extraction now sees PIT-safe entry context — entry rsi14 and prior 5d return fetched through the loader registry as of buy dt , with graceful offline/no-data degradation 302 https://github.com/HKUDS/Vibe-Trading/pull/302 , follows 295 https://github.com/HKUDS/Vibe-Trading/issues/295 , thanks @Robin1987China . The main Web UI panels now use reactive English / zh-CN translations across charts, chat, Alpha Library, Correlation, and Run Detail 301 https://github.com/HKUDS/Vibe-Trading/pull/301 , thanks @skloxo . Remote same-origin Web UI deployments with API AUTH KEY can post and upload again after the CSRF hardening, while mismatched cross-site origins remain blocked 304 https://github.com/HKUDS/Vibe-Trading/pull/304 , thanks @Hinotoi-agent . - 2026-06-23 🛡️ Local API CSRF hardening : a malicious web page can no longer drive unsafe cross-site requests POST/PUT/DELETE against the loopback API — CORS blocks reading the response but not the side effect, so loopback dev-mode trust now applies the existing cross-site guard to unsafe methods before honoring it. Safe methods and local CLI / non-browser uploads are unaffected 293 https://github.com/HKUDS/Vibe-Trading/pull/293 , thanks @Hinotoi-agent . - 2026-06-22 🔧 Live-authorize OAuth fix + Alpha Zoo headline fix : connector authorize now holds the OAuth handshake open through a multi-minute broker sign-in tunable via VIBE LIVE AUTHORIZE TIMEOUT SECONDS and no longer spawns a competing callback server on retry, so the token actually persists 281 https://github.com/HKUDS/Vibe-Trading/pull/281 , closes 259 https://github.com/HKUDS/Vibe-Trading/issues/259 , thanks @Robin1987China . The Alpha Zoo page no longer prints its alpha count twice 287 https://github.com/HKUDS/Vibe-Trading/pull/287 , closes 286 https://github.com/HKUDS/Vibe-Trading/issues/286 , thanks @digger-yu . Scheduled research also picked up end-to-end usage docs 288 https://github.com/HKUDS/Vibe-Trading/pull/288 . - 2026-06-21 ⏰ Scheduled-research executor + Reports library + post-backtest attribution : scheduled research now runs end to end — a default-off background executor VIBE TRADING ENABLE SCHEDULER fires due interval/cron jobs through the session runtime 278 https://github.com/HKUDS/Vibe-Trading/pull/278 , thanks @mvanhorn, closing 254 https://github.com/HKUDS/Vibe-Trading/issues/254 . A newpage lists, searches, and filters report-worthy runs with links into Run Detail + Compare /reports Run Library 224 https://github.com/HKUDS/Vibe-Trading/pull/224 , thanks @LemonCANDY42 . And after every backtest the agent now runs layered attribution — trade-level winners/losers, beta regression, market-regime analysis, and a Monte Carlo permutation test, gated by data availability and routing 280 https://github.com/HKUDS/Vibe-Trading/pull/280 , thanks @shadowinlife . - 2026-06-20 🔬 Research Autopilot loop closes Phase 3 + loader OHLC integrity guard + 4 academic alphas : Research Autopilot now runs hypothesis → signal-engine → backtest end to end — scaffold signal engine writes a contract-correct engine and link autopilot backtest feeds run metrics back to the hypothesis 68 tools 267 https://github.com/HKUDS/Vibe-Trading/pull/267 . A structural OHLC sanity check drops dirty bars high < low , non-positive prices, bad bracketing centrally at the loader boundary, guarding every data source 274 https://github.com/HKUDS/Vibe-Trading/pull/274 , thanks @Shizoqua . And the academic alpha family grows 6 → 10 — Jegadeesh reversal, George-Hwang 52-week-high, Amihud illiquidity, Harvey-Siddique skew 456 factors 277 https://github.com/HKUDS/Vibe-Trading/pull/277 , thanks @Robin1987China . - 2026-06-19 🚀 v0.1.10 — Global data layer : market-data sources grow 10 → 18 free Eastmoney / Sina / Stooq / Yahoo + key-gated Finnhub / Alpha Vantage / Tiingo / FMP , ban-risk fallback plus 18 read-only data tools fund flow, dragon-tiger, northbound, margin, block trades, SEC EDGAR + XBRL, financials, options chains, full-market screening… across A-share / US / HK, all over MCP. Also bundles everything since 0.1.9 — 10 broker connectors, alpha compare , the provider-reliability overhaul, and the opt-in data cache. pip install -U vibe-trading-ai - 2026-06-18 🔬 Research Autopilot Phase 1 + a local Data Bridge loader, + a Discord security notice : new run research autopilot + generate backtest config wire Hypothesis → Research Goal → backtest end to end now 50 tools , and aloader reads OHLCV straight from your own local CSV / Parquet / DuckDB files 260 https://github.com/HKUDS/Vibe-Trading/pull/260 , 252 https://github.com/HKUDS/Vibe-Trading/pull/252 , thanks @Robin1987China , alongside DeepSeek DSML tool-call parsing and an identifier-containment hardening wave.⚠️ Security: the old community Discord invite now points to a server we don't control running a fake Collab.Land wallet-"verification" phishing scam — removed everywhere; the only official Discord is the HKUDS server discord.gg/6TdQnT5xcF https://discord.gg/6TdQnT5xcF , and we'll never ask you to connect a wallet. - 2026-06-17 🧩 Install compatibility + Opus/Kimi provider fixes : Baseline pip install vibe-trading-ai no longer pulls the optional pyharmonics / ta dependency chain; harmonic detection now lives behind vibe-trading-ai harmonic while the bundled detector remains available 250 https://github.com/HKUDS/Vibe-Trading/pull/250 , closes 249 https://github.com/HKUDS/Vibe-Trading/issues/249 . The agent loop also avoids assistant-prefill handoff messages rejected by Opus 4.8+, and Kimi/Moonshot can override the client User-Agent with MOONSHOT USER AGENT 248 https://github.com/HKUDS/Vibe-Trading/pull/248 , closes 246 https://github.com/HKUDS/Vibe-Trading/issues/246 and 204 https://github.com/HKUDS/Vibe-Trading/issues/204 ; follow-up tests now directly cover background-result and auto-compact handoff paths 251 https://github.com/HKUDS/Vibe-Trading/pull/251 . - 2026-06-16 🛡️ Security/API hardening + GLM/Zhipu alias : Settings writes require auth when configured 245 https://github.com/HKUDS/Vibe-Trading/pull/245 ; API shell-capable tools require explicit VIBE TRADING ENABLE SHELL TOOLS=1 opt-in 243 https://github.com/HKUDS/Vibe-Trading/pull/243 ; local shutdown requires auth when an API key is configured 241 https://github.com/HKUDS/Vibe-Trading/pull/241 ; and untrusted loopback-looking hosts are rejected instead of treated as local 242 https://github.com/HKUDS/Vibe-Trading/pull/242 . Runtime edges also got cleaned up: Web chat syncs completed attempts 236 https://github.com/HKUDS/Vibe-Trading/pull/236 , run cards emit strict JSON for non-finite metrics 238 https://github.com/HKUDS/Vibe-Trading/pull/238 , malformed RSSHUB TIMEOUT S / RSSHUB FETCH BUDGET S falls back safely 240 https://github.com/HKUDS/Vibe-Trading/pull/240 , and ddgs retry fallback is regression-covered 239 https://github.com/HKUDS/Vibe-Trading/pull/239 . GLM/Zhipu is now a first-class provider alias with model-name inference 247 https://github.com/HKUDS/Vibe-Trading/pull/247 , closes 237 https://github.com/HKUDS/Vibe-Trading/issues/237 . - 2026-06-15 🧭 Web-search resilience + Web UI run-continuity fixes : web search no longer fails when a single engine is rate-limited — it now queries several free, no-key engines in order DuckDuckGo, Google, Bing, Brave, Mojeek, Yahoo with retry/backoff, treats "no results" as an empty answer rather than an error, and returns an actionable message instead of a bare ❌ when every engine is throttled override the engine list with VIBE TRADING SEARCH BACKENDS 232 https://github.com/HKUDS/Vibe-Trading/pull/232 , closes 231 https://github.com/HKUDS/Vibe-Trading/issues/231 , thanks @Ethan-sun01 . In the Web UI, switching pages during a run no longer freezes it — the chat re-subscribes to the live stream and replays missed progress on return 234 https://github.com/HKUDS/Vibe-Trading/pull/234 — and the Stop button now takes effect mid-stream and between tools instead of only at iteration boundaries 235 https://github.com/HKUDS/Vibe-Trading/pull/235 , closing both halves of 229 https://github.com/HKUDS/Vibe-Trading/issues/229 thanks @kalkinj . The baostock loader also accepts native sh.601398 / sz.000001 codes alongside tushare-style 601398.SH 230 https://github.com/HKUDS/Vibe-Trading/pull/230 , thanks @bhlt . - 2026-06-14 📊 Per-run token usage + progressive Run Detail charts : Every agent run now persists provider-reported token usage as a run-scoped llm usage.json — provider/model, aggregate totals, and per-iteration counts — surfaced additively on /runs/{id} , so a finished run's token cost stays auditable after the live stream is gone provider-reported only; no prompt/content capture, no price estimation 223 https://github.com/HKUDS/Vibe-Trading/pull/223 , thanks @LemonCANDY42 . The Run Detail page no longer loads every symbol's candlesticks up front: the default /runs/{id} response is unchanged, but the UI now renders the run summary first and loads each symbol's chart on demand through opt-in ?chart payload=summary / ?chart symbol= modes, with per-symbol loading state and a load-all-with-progress control 225 https://github.com/HKUDS/Vibe-Trading/pull/225 , thanks @LemonCANDY42 . Two loader fixes close the cycle: yfinance's exclusive end boundary no longer drops the final requested trading day — the download now passes end + 1 day while cache keys keep the original range 226 https://github.com/HKUDS/Vibe-Trading/pull/226 , thanks @gyx09212214-prog — and a malformed CCXT TIMEOUT MS / OKX TIMEOUT S value now warns and falls back to its default instead of raising at import and blocking startup 227 https://github.com/HKUDS/Vibe-Trading/pull/227 , thanks @gyx09212214-prog . - 2026-06-13 ↩️ Resume a past session by ID from the CLI : The interactive CLI now prints the session-id on exit, with a copy-paste vibe-trading resume <session-id hint — so locating the trace for a finished run no longer means guessing which folder under agent/sessions/ is newest by timestamp. The new vibe-trading resume <session-id subcommand reopens that exact session and replays its recent turns into the loop; an unknown id fails fast instead of silently starting a blank session 218 https://github.com/HKUDS/Vibe-Trading/pull/218 , thanks @zwrong . - 2026-06-12 🩺 Provider reliability overhaul — DeepSeek hangs, Kimi access, streaming liveness : A cluster of provider reports — DeepSeek runs stuck on "Agent is working…" 208 https://github.com/HKUDS/Vibe-Trading/issues/208 , thanks @XYWOX , reached max iterations masking empty model responses 203 https://github.com/HKUDS/Vibe-Trading/issues/203 , thanks @mojianliang , the UI never recovering after a stall 195 https://github.com/HKUDS/Vibe-Trading/issues/195 , thanks @mafia23 , and Kimi rejecting the client 204 https://github.com/HKUDS/Vibe-Trading/issues/204 , thanks @liao497 — shared one root: every OpenAI-compatible provider ran through a single shim that applied DeepSeek/Kimi/Gemini quirks globally and silently swallowed stream failures. Provider-specific behavior now lives in an explicit capability layer — reasoning capture/replay, Gemini thought signatures, the Kimi User-Agent , OpenRouter's reasoning body are each gated to their own provider instead of cross-contaminating. Reasoning-only streams show a live "Reasoning…" indicator instead of dead air; a stream failure raises a contextual provider stream error with one automatic retry for transient resets deterministic 4xx fail fast instead of silently falling back to a slow non-streaming call; an empty model response is reported as empty model response instead of "max iterations"; SSE heartbeats no longer break reconnect replay; and a stuck read-only tool times out instead of hiding behind heartbeats forever. A newprints a redacted provider/model/package/proxy snapshot for one-command triage of environment-side hangs. DeepSeek users can opt into the official native adapter with vibe-trading provider doctor pip install "vibe-trading-ai deepseek " , and kimi-k2.x's temperature=1 requirement is applied automatically — the Kimi path is verified end-to-end against the live API tool calls + strict multi-turn reasoning replay on kimi-k2.6 . - 2026-06-11 🐝 Swarm workers now pull market data through the loader layer : An investment-committee run on NVDA exposed a chain of gaps — workers wrote ad-hoc yfinance scripts, trusted a malformed latest bar volume present, OHLC empty , leaked NaN into non-strict JSON, and a context-free continuation prompt re-routed to the wrong preset 198 https://github.com/HKUDS/Vibe-Trading/issues/198 , thanks @BillDin for an exceptional diagnosis plus both fixes . Swarm workers now get a local get market data tool backed by the same normalized loader registry as MCP — strict JSON, non-finite floats serialize as null — wired into every market-data preset 21 workers across 13 presets with a prompt policy that steers OHLCV work tool-first 199 https://github.com/HKUDS/Vibe-Trading/pull/199 ; run swarm takes an explicit preset name and refuses ambiguous continuation fragments instead of silently falling back to equity research team 200 https://github.com/HKUDS/Vibe-Trading/pull/200 . Grounding got smarter too: a bare US ticker like NVDA in a swarm prompt is promoted to NVDA.US stopword-guarded , so workers start from authoritative pre-fetched prices. The tool joins the main agent registry as well — 48 tools now. Also: your Docker data now survives updates — persistent memory, the session search index, user-created skills, shadow accounts and broker config live in named volumes, so docker compose up --build no longer wipes them 197 https://github.com/HKUDS/Vibe-Trading/issues/197 , thanks @FlyerJ . - 2026-06-10 🐳 Docker reaches a host-side Ollama out of the box : Inside the container localhost is the container itself, so the shipped OLLAMA BASE URL=http://localhost:11434 failed the LLM preflight for every Dockerized Ollama setup. docker-compose.yml now defaults to http://host.docker.internal:11434 export OLLAMA BASE URL to point elsewhere and adds the host-gateway extra hosts mapping so the same file works on Linux as well as Docker Desktop 196 https://github.com/HKUDS/Vibe-Trading/pull/196 , thanks @ShahNewazKhan . - 2026-06-09 🔑 Clearer error when the Web UI is opened from another machine : Reaching the chat from a non-loopback client another machine, a VM host, a phone on your LAN without API AUTH KEY set returned 403 on every sensitive endpoint — sending a message, listing sessions, live status — but the chat only showed a generic "Failed to send message, please retry." The send path now surfaces the real reason — "Remote API access requires an API key. Add it in Settings, or run the backend on localhost for local-only use." — and the README's web-UI setup spells out the localhost-vs-LAN rule plus the three fixes browse via localhost on the same machine; set API AUTH KEY and enter it once in Settings; or VIBE TRADING TRUST DOCKER LOOPBACK=1 for Docker Desktop's host gateway 191 https://github.com/HKUDS/Vibe-Trading/issues/191 , thanks @mafia23 . - 2026-06-08 🔧 Gemini 3.x multi-turn tool-calling fix : This completes the Gemini 3.x thinking-model fix. The 6/05 round-trip 176 https://github.com/HKUDS/Vibe-Trading/pull/176 only covered in-memory history, but the real agent loop replays history as OpenAI-format dicts where LangChain dropped the per-tool-call thought signature before the request was built — so multi-turn tool calling still 400'd with missing thought signature . It is now re-attached at the single convert input chokepoint both invoke and stream pass through parallel calls, where only the first of N is signed, included 184 https://github.com/HKUDS/Vibe-Trading/pull/184 , thanks @ngoanpv . - 2026-06-07 🐝 Live swarm status in the chat timeline : When the agent launches a multi-agent swarm investment committee, quant desk, risk committee, … , the chat now renders an inline status card that streams each worker's state — waiting / running / done / failed / blocked / retrying — in real time, the same per-agent visibility the standalone swarm dashboard already had. Runtime events are bridged into the session SSE stream without changing the existing /swarm/runs API, and a finished card rehydrates from the final run swarm result on reconnect or history replay 188 https://github.com/HKUDS/Vibe-Trading/pull/188 , thanks @BillDin . Preset routing also got sharper: an explicitly named preset e.g. investment committee , with or without underscores now wins over keyword scoring, and the bare IV derivatives keyword no longer false-matches inside ordinary words like "g iv en" 189 https://github.com/HKUDS/Vibe-Trading/pull/189 , thanks @BillDin . - 2026-06-06 ⚖️ Alpha compare — head-to-head across CLI, Web UI, REST & agent : A new alpha compare benches a hand-picked shortlist of Alpha Zoo alphas against each other on a universe and period, then ranks them by IC mean/std, IR, IC-positive ratio or sample count — each with its gap to the leader. Unlike a full-zoo bench it evaluates only the alphas you name a new run bench only=… subset filter , so comparing three alphas no longer scores all 191 in their zoo. One shared core powers every surface: vibe-trading alpha compare <id1 <id2 … --sort ir CLI , a Compare view in the Alpha Zoo Web UI tick alphas in the catalogue → one-click compare with a streamed ranking table , POST /alpha/compare + SSE REST , and a read-only alpha compare agent tool 47 tools now . - 2026-06-05 🇮🇳 Dhan + Shoonya connectors India — 10 brokers total : The connector-first trading layer adds Dhan and Shoonya for the Indian market NSE/BSE equities + F&O , bringing the roster to ten brokers. Both are paper + read-only — like Longbridge, their APIs expose no runtime paper/live discriminator, so their place order / cancel order hard-refuse any non-paper config at the first line the rule: a broker with no structural paper/live guard is capped at paper + read-only 181 https://github.com/HKUDS/Vibe-Trading/pull/181 , closes 174 https://github.com/HKUDS/Vibe-Trading/issues/174 . This cycle also fixes Gemini 2.5 / 3.x thinking models : their per-tool-call thoughtSignature now round-trips through the OpenAI-compatible path, so multi-turn function calling no longer fails with INVALID ARGUMENT 176 https://github.com/HKUDS/Vibe-Trading/pull/176 , closes 170 https://github.com/HKUDS/Vibe-Trading/issues/170 , thanks @mvanhorn & @jliu6789 . Chinese docstrings landed on all 452 Alpha Zoo factors 180 https://github.com/HKUDS/Vibe-Trading/pull/180 , thanks @LeeCQiang , and a frontend test suite 197 vitest tests plus backend auth / path-traversal / CORS security tests joined CI 175 https://github.com/HKUDS/Vibe-Trading/pull/175 , thanks @sambazhu . - 2026-06-04 🗃️ Opt-in local data cache for all 7 data sources : A new VIBE TRADING DATA CACHE switch lets every backtest loader — tushare, okx, ccxt, akshare, mootdx, yfinance, futu — cache settled historical bars under ~/.vibe-trading/cache user home, never the repo , so repeated and long-horizon / cross-market backtests skip the network and avoid provider rate limits. Off by default. Batch and connection loaders yfinance, futu skip the bulk download / FutuOpenD connection entirely on a full cache hit, a staleness guard never caches a range ending today its last bar is still forming , and cached frames round-trip byte-identical to freshly fetched ones 177 https://github.com/HKUDS/Vibe-Trading/pull/177 , thanks @mvanhorn . A new contributor guide for AI / automation-assisted PRs also landed, mapping safe local checks and high-risk broker/MCP/credential surfaces 173 https://github.com/HKUDS/Vibe-Trading/pull/173 . - 2026-06-03 🧹 Community triage + trace correlation : Tool-call trace entries now carry the originating call id , so a tool result can be matched back to its tool call when replaying a run trace — arg previews stay truncated to keep trace files small 168 https://github.com/HKUDS/Vibe-Trading/pull/168 , thanks @zwrong . Source comments no longer point at an internal-only docs path that external contributors couldn't find 166 https://github.com/HKUDS/Vibe-Trading/issues/166 , thanks @jaleelpersonal . Also clarified that the langchain-community resolver warning on install is a harmless leftover-package notice, not a failure 167 https://github.com/HKUDS/Vibe-Trading/issues/167 , and scoped Gemini 2.5/3.0 thoughtSignature round-tripping for function calls as a help wanted task with a full fix plan 170 https://github.com/HKUDS/Vibe-Trading/issues/170 , thanks @jliu6789 . - 2026-06-02 🔌 Six new broker connectors Tiger / Longbridge / Alpaca / OKX / Binance / Futu : The connector-first trading layer gains a direct-SDK transport alongside IBKR local and Robinhood MCP . Each connector exposes read-only account / positions / orders / quote / history plus paper-account order placement — test your strategies across these broker paper accounts. Five of them Tiger, Alpaca, OKX, Binance, Futu also support bounded, mandate-gated order placement behind the same safety model as Robinhood: a user-committed mandate symbol universe / order size / exposure / leverage / daily cap , a filesystem kill switch, a fail-closed pre-trade gate, and a full audit ledger. Longbridge is paper + read-only only its API exposes no runtime paper/live discriminator . Every paper/live distinction is a structural per-broker guard — account-id format, host separation, demo flag, or trade environment. New trading place order / trading cancel order tools; HK and A-share asset classes added to the mandate universe. Experimental / use at your own risk. - 2026-06-01 🚀 v0.1.9 released pip install -U vibe-trading-ai : Rolls up everything since 0.1.8. Connector-first broker profiles IBKR local read-only TWS / IB Gateway + Robinhood Agentic Trading behind OAuth, a committed mandate, order guard, audit ledger, and instant halt . Research Goal runtime across CLI / REST / MCP / Web. A swarm pass — live reconcile + MCP keepalive, operator-configured worker MCP tools, a strict alpha-bench random control, and a new retry run to relaunch failed/stale runs 36 MCP tools now . The agent/cli/ package refactor with a refreshed terminal UI, the mootdx no-token A-share loader, and a robustness pass across backtest / agent loop / sessions. --version now always matches the installed package, fixing the 0.1.8 drift 156 https://github.com/HKUDS/Vibe-Trading/issues/156 . - 2026-05-31 🔌 Connector-first broker architecture IBKR + Robinhood : Trading access now starts from a selectable connector profile instead of separate broker/live entry points. vibe-trading connector list/use/check/account/positions/orders/quote/history and the MCP trading tools share the same selected profile, where paper/live is an attribute of the connector. IBKR can be used immediately through a local read-only TWS / IB Gateway profile, while the official IBKR remote MCP path is seeded as an OAuth mcp.read probe until stable read tool names are available. Robinhood Agentic Trading remains the bounded live MCP connector behind OAuth, a committed mandate, order guard, audit ledger, and instant halt. - 2026-05-30 🧰 Robustness pass — backtest, agent loop, sessions : LLM-generated signal engines now pass pre-flight interface validation before instantiation, catching circular self-imports, a missing generate , non-defaulted init args, and wrong return types with actionable JSON errors instead of raw tracebacks 149 https://github.com/HKUDS/Vibe-Trading/pull/149 ; a follow-up routes source-level AST validation errors through the same clean JSON envelope. The agent loop no longer burns all 50 iterations into a failed status with no output — it mirrors the swarm worker's wrap-up nudge at 80% of the iteration budget and drops tool definitions on the last iteration to force a final text answer 148 https://github.com/HKUDS/Vibe-Trading/pull/148 , guarded to fire only mid-run so it never displaces research-goal context. Session message writes now flush + fsync each append so expensive AI responses survive a mid-write crash, and the read path skips corrupted JSONL lines logging the first 200 chars for recovery instead of 500-ing the whole /messages endpoint 147 https://github.com/HKUDS/Vibe-Trading/pull/147 . The Web composer also fixes IME Enter handling so a composition-confirming Enter no longer submits mid-word 146 https://github.com/HKUDS/Vibe-Trading/pull/146 . - 2026-05-29 🔐 Robinhood Agentic Trading support opt-in, bounded autonomy : Adds support for Robinhood Agentic Trading remote MCP, OAuth . Off and read-only by default; the agent acts only inside a user-committed mandate symbols / order size / exposure / leverage / daily cap , with a filesystem-level instant kill switch, preemptive flatten, mandate auto-expiry, a full audit ledger, and a persistent autonomous runner. No custody, no venue — the broker holds funds and executes; we only relay intent. Experimental / use at your own risk. - 2026-05-28 🧪 Swarm safety + strict alpha gate + worker MCP : Swarm DAG blocks downstream tasks when upstream fails 145 https://github.com/HKUDS/Vibe-Trading/pull/145 . New run bench strict adds a same-universe random control + OOS split to catch factors that just track market beta 143 https://github.com/HKUDS/Vibe-Trading/pull/143 , thanks @Soli22de . Swarm workers can call operator-configured external MCP servers, with trust boundary pinned 142 https://github.com/HKUDS/Vibe-Trading/pull/142 , thanks @shadowinlife . - 2026-05-27 📊 mootdx A-share data source + output polish : New mootdx loader speaks the native 通达信 TCP protocol for A-share OHLCV no auth, no IP rate-limit, daily + intraday with 25-page walk-back pagination , slotting between tushare and akshare in the fallback chain 107 https://github.com/HKUDS/Vibe-Trading/issues/107 . CCXT loader now reads HTTP PROXY/HTTPS PROXY/ALL PROXY so Binance/OKX public data works from restricted networks 126 https://github.com/HKUDS/Vibe-Trading/pull/126 , thanks @ruok808 . Final-answer rendering also dropped the ugly full-width --- horizontal separators on CLI and Web: the system prompt now nudges the agent toward markdown tables and headings, the CLI renderer strips standalone HRs as defense-in-depth, and the chat bubble hides any <hr that slips through 139 https://github.com/HKUDS/Vibe-Trading/issues/139 , thanks @sdwxm188 . - 2026-05-26 ✅ Research Goal lifecycle closure : Goal mode now behaves like a real task runner: Web UI goal creation creates or binds the session and immediately sends the kickoff turn; active goals can be continued, edited, cancelled, and completed across Web/API/CLI/MCP; and the agent advances from the current goal snapshot criteria, evidence, claims, open items instead of only the original prompt. Covered-but-still-active goals now enter an audit/status update instead of stopping silently, with regression coverage across backend, CLI, MCP, and frontend events. - 2026-05-25 🧼 Cleaner chat UI + composer workflow : The Web UI keeps chat focused on the next action: upload, swarm, and research-goal modes now live behind the composer + menu instead of floating panels. Active context appears above the input as compact chips, and goal details expand inline only when needed. The UI also drops the old custom i18n layer in favor of direct English copy, gates Full Report cards to report-worthy runs, and hardens local dev startup/status reporting for reliable browser smoke tests. - 2026-05-24 🎯 Research Goal runtime : Added a session-scoped Research Goal layer across backend, CLI, API/MCP, SSE, and Web UI. Goals persist claims, acceptance criteria, evidence rows, budgets, and completion policy; agent tools can create goals and attach evidence; /goal gives the CLI a direct entry point; REST/MCP expose goal snapshots and evidence writes; SSE keeps chat clients fresh. Follow-up audit fixes locked down verified evidence, blocked live-trading risk tiers through agent tools, wired CLI-created goals into later turns, cleaned goal ledgers on session deletion, enabled replay-all, and fixed cross-session frontend races. - 2026-05-23 🖥️ Interactive CLI refresh : The terminal front door now opens with a larger Vibe-Trading banner, a cleaner prompt divider, prior-turn recap, post-run timing, and a Claude Code-style activity rail for live agent work. Tool calls, web/data fetches, shell-style actions, Markdown answers, and pipe tables render in a more readable transcript, while piped or non-TTY runs keep plain-text output for automation. Generated CLI screenshots are now treated as local artifacts instead of committed docs files, keeping the repository lighter. - 2026-05-22 🧭 Swarm recovery + MCP keepalive : Swarm status now reconciles from live task files on every read, so API/MCP/SSE/list views recover crashed or stale runs instead of showing permanent running snapshots. run swarm sends MCP progress heartbeats while it polls, with a fixed first frame of swarm started run id=<id for clients that reconnect after transport drops; workers now heartbeat through LLM streaming, grounding fetches, and tool execution. The stale-run reaper uses per-run thresholds and derives terminal status from task states, SwarmTool no longer cancels a still-running team just because its wait budget elapsed, and MCP clients can call reap stale runs for explicit cleanup. Today's DX pass also refreshed provider default models and aligned CI syntax checks with the new agent/cli/ package. 22 new regressions cover hydration, terminal recovery, stale reaping, keepalive cadence, env parsing, and heartbeat wiring; the full swarm/MCP suite is at 169 passed, 4 skipped. - 2026-05-21 🧱 CLI package refactor : agent/cli.py 3216 LOC split into the agent/cli/ package — interactive front door, slash router, Rich components, plus a legacy.py shim that preserves every subcommand and re-exports every public symbol so cli.cmd / cli. INIT ENV PATH / cli.Confirm keep working. New FastAPI middleware serves the SPA shell when a browser opens /runs/{id} or /correlation directly; same narrowing landed in the Vite dev proxy. Version unified via cli/ version.py no more drift between --version and the banner , python -m cli restored via main .py , and the chat-gate narrowed so chat --help / chat extra reach legacy argparse instead of being swallowed by the REPL. - 2026-05-20 🔬 Hypothesis Registry CLI : Closes the CLI side of the Hypothesis Registry shipped backend-only on 2026-05-16. vibe-trading hypothesis list prints a Rich table or JSON --status filter, --limit ; show <id renders a detail panel including linked run cards; invalidate <id --note "..." flips status to rejected while preserving prior invalidation notes when --note is omitted. Honors the existing VIBE TRADING HYPOTHESES PATH env override and adds a per-invocation --path . 22 new tests cover wiring, JSON output, status filter, limit, missing-id errors, and note persistence. - 2026-05-19 ✨ Live tool feedback + graceful cancel : Long-running tools backtests, large PDFs, swarm workers no longer look frozen. Each tool call now emits a 3-second heartbeat plus structured per-stage progress — run backtest shows phase markers validate / simulate / finalize , read document ticks per page on PDF or per sheet on Excel, read url marks fetch / parse . The CLI Rich Live dashboard renders a Unicode spinner, ASCII progress bar, ETA, and stacks up to 3 parallel tools keyed by name; the frontend chat ships a new ToolProgressIndicator with rAF-coalesced renders, ARIA role="status" + hidden native <progress for screen readers, and a determinate ProgressRing SVG when total is known. First Ctrl+C during a CLI run now calls agent.cancel for graceful exit current step finishes, trace closes cleanly ; a second within 2s force-quits. Reusable primitives extracted along the way: ProgressBar.tsx and lib/tools.ts shared tool-name i18n . - 2026-05-18 🧹 Cleanup pass + three latent bug fixes : CompositeEngine no longer misroutes bare Chinese-futures codes like RB2410 to GlobalFuturesEngine — is china futures moved into a shared market hooks module with a case-normalized product table and a non-CN exchange guard, plus 9 new regression cases. Session FTS5 indexes now persist timestamps so cross-session search can sort by date; the same path also fixed a re-upsert that was wall-clocking every session's started at . The Vite dev-mode proxy gained the missing /alpha entry so the AlphaZoo page resolves on npm run dev . tests/test e2e harness v2.py real-LLM e2e suite is now gated behind VIBE TRADING RUN LIVE E2E=1 so CI no longer changes shape based on env-key presence. Ruff per-file-ignores added for the factor zoo 3783 → 0 F401 noise , frontend tsconfig enables noUnusedLocals / noUnusedParameters as regression guards, and 76 unused vw = vwap ... boilerplate lines were dropped from gtja191 alphas. Net -918 LOC . - 2026-05-17 🧬 Alpha Zoo v1 0.1.8 : 452 pre-built quant alphas across 4 zoos — qlib158 Microsoft Qlib, Apache-2 attribution , alpha101 Kakushadze 101 Formulaic Alphas, paper rewrite from arXiv:1601.00991 , gtja191 Guotai Junan 2014 short-horizon factor report , and academic Fama-French 5 + Carhart price-based proxies . One-line CLI to bench any zoo on your universe: vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025 . Ships with AST purity gate, lookahead-guard test, pytest-socket network kill-switch, per-zoo LICENSE.md, and a Developer Certificate of Origin DCO workflow for community PRs. Auto-rendered Alpha Library at vibetrading.wiki/alpha-library/ https://vibetrading.wiki/alpha-library/ + research-lab post Which of the 191 GTJA alphas still work in 2026? https://vibetrading.wiki/research-lab/posts/alpha-191-in-2026.html . - 2026-05-16 🧪 Research spine update : Added a backend Hypothesis Registry with create hypothesis , update hypothesis , link backtest , and search hypotheses ; external-content readers now attach warning-only security warnings ; and Shadow Account scanning now uses deterministic OHLCV feature evaluation instead of the old calendar-phase stub. - 2026-05-15 🪪 The run detail page now surfaces the Trust Layer run card alongside metrics and artifacts, completing the UI side of the run card.json work landed on 2026-05-12. PersistentMemory.add was also hardened on length, empty/whitespace-only names, and C0/C1 control bytes from the 108/ 109/ 110 triage 112 https://github.com/HKUDS/Vibe-Trading/pull/112 , thanks @Teerapat-Vatpitak . - 2026-05-14 🌐 the public wiki is now live at vibetrading.wiki https://vibetrading.wiki/ with docs, tutorials, Research Lab, and Alpha Library sections deployed through Cloudflare Pages. Persistent memory is also inspectable from the CLI via vibe-trading memory list/show/search/forget 102 https://github.com/HKUDS/Vibe-Trading/pull/102 , thanks @Teerapat-Vatpitak , and memory tokenization/slugs now support Thai, Arabic, Hebrew, and Cyrillic text 104 https://github.com/HKUDS/Vibe-Trading/pull/104 . - 2026-05-13 🧭 Swarm runs now ground workers with fetched market data and cleaner persisted reports 93 https://github.com/HKUDS/Vibe-Trading/pull/93 , 84 https://github.com/HKUDS/Vibe-Trading/pull/84 . - 2026-05-12 🧾 Backtests now emit run card.json and run card.md alongside artifacts for reproducible research runs. - 2026-05-11 🧭 Memory slugs, swarm accounting, and CLI preflight : Persistent memory now preserves CJK characters when generating file slugs, preventing silent filename collisions for Chinese/Japanese/Korean notes 95 https://github.com/HKUDS/Vibe-Trading/pull/95 , thanks @voidborne-d . Swarm run totals now prefer provider-reported token usage with the existing estimate fallback 94 https://github.com/HKUDS/Vibe-Trading/pull/94 , thanks @Teerapat-Vatpitak , and the CLI run UI gained a startup preflight check for common environment issues 96 https://github.com/HKUDS/Vibe-Trading/pull/96 , thanks @ykykj . - 2026-05-10 🧱 Regression guardrails + run metadata : Memory recall now treats underscores as token boundaries, so snake case saved memories such as mcp wiring test match natural-language queries like "mcp wiring" 87 https://github.com/HKUDS/Vibe-Trading/pull/87 , thanks @hp083625 . The MCP server has a subprocess smoke test covering initialize → tools/list → tools/call to guard the first-call deadlock path 86 https://github.com/HKUDS/Vibe-Trading/pull/86 , while low-risk hardening landed for Windows path-sensitive tests, API best-effort exception handling, backtest run dir allowed-root validation, and SwarmRun provider/model metadata 88 https://github.com/HKUDS/Vibe-Trading/pull/88 , 90 https://github.com/HKUDS/Vibe-Trading/pull/90 , 91 https://github.com/HKUDS/Vibe-Trading/pull/91 , 92 https://github.com/HKUDS/Vibe-Trading/pull/92 , thanks @Teerapat-Vatpitak . - 2026-05-09 🛡️ API path hardening + MCP server stability : API run/session routes now validate path IDs before lookup, rejecting malformed newline-containing parameters and pinning the behavior in the auth/security regression suite 80 https://github.com/HKUDS/Vibe-Trading/pull/80 , thanks @SJoon99 . The MCP server now pre-warms the tool registry on the main thread before serving tools/call , avoiding a first-call deadlock in lazy tool discovery 85 https://github.com/HKUDS/Vibe-Trading/pull/85 , thanks @Teerapat-Vatpitak . The Vite dev proxy also honors VITE API URL for non-default backend targets 82 https://github.com/HKUDS/Vibe-Trading/pull/82 , thanks @voidborne-d . - 2026-05-08 🧾 Tushare statement fields in filters : A-share daily backtests can now request PIT-safe financial statement fields through fundamental fields , so signal engines can screen on income total revenue , income n income , balancesheet total hldr eqy exc min int , fina indicator roe , and similar table-prefixed columns after their announcement/disclosure dates 76 https://github.com/HKUDS/Vibe-Trading/pull/76 , thanks @mrbob-git . Follow-up hardening makes explicit statement-field requests fail fast if Tushare enrichment cannot run, instead of silently falling back to raw price bars 77 https://github.com/HKUDS/Vibe-Trading/pull/77 . - 2026-05-07 📈 Tushare fundamentals + community triage : Added a point-in-time TushareFundamentalProvider contract for fundamental research workflows, with regression coverage for the project TUSHARE TOKEN environment path 74 https://github.com/HKUDS/Vibe-Trading/pull/74 . Community triage also clarified that Vibe-Trading keeps rapid iteration focused on one UI language for now, avoids adding redundant search dependencies while DuckDuckGo-backed web search is already bundled, and treats unofficial hosted deployments as untrusted places for API keys or data-source tokens. - 2026-05-06 🚀 v0.1.7 released Release notes https://github.com/HKUDS/Vibe-Trading/releases/tag/v0.1.7 , pip install -U vibe-trading-ai : Security-boundary hardening is now published on PyPI and ClawHub, covering safer API/read/upload/file/URL/generated-code/shell-tool/Docker defaults while keeping localhost CLI/Web UI workflows low-friction. This cycle also includes Web UI Settings, correlation heatmap, OpenAI Codex OAuth, A-share pre-ST filtering, interactive CLI UX, swarm preset inspection, dividend analysis, dev workflow polish, and audited frontend build-dependency floors. Thanks to the 0.1.7 contributors and to lemi9090 S2W for coordinated security validation. - 2026-05-05 🛡️ Security boundary follow-up : Completes the remaining security-boundary hardening around explicit CORS origins, Settings credential indicators, web URL reading, and Shadow Account code generation, with regression tests added for each path. Normal localhost CLI/Web UI workflows stay the same; remote deployments should continue using API AUTH KEY and explicit trusted origins. - 2026-05-04 🖥️ Interactive CLI UX + CI cleanup : Interactive mode now has a live bottom status bar showing provider/model, session duration, last-run latency, and cumulative tool-call stats, plus prompt history navigation and cursor editing with arrow keys via prompt toolkit 69 https://github.com/HKUDS/Vibe-Trading/pull/69 . The CLI still falls back to Rich prompts when prompt toolkit or a TTY is unavailable. CI path expectations were also aligned with the hardened file-import sandbox and cross-platform /tmp resolution, returning main to green . bb67dc7 - 2026-05-03 🛡️ Security hardening patch : Tightens default API authentication for non-local deployments, protects sensitive run/session/swarm reads, restricts upload and local file-reading boundaries, gates shell-capable tools by entry point, validates generated strategy loading before import, and runs the Docker image as a non-root user with a localhost-only published port by default. Local CLI and localhost Web UI workflows remain low-friction; remote API/Web deployments should set API AUTH KEY . - 2026-05-02 🧭 Dividend analysis + sharper roadmap : Added the dividend-analysis skill for income stocks, payout sustainability, dividend growth, shareholder yield, ex-dividend mechanics, and yield-trap checks, pinned by bundled-skill regression tests. The public roadmap now focuses on upcoming work: Research Autopilot, Data Bridge, Options Lab, Portfolio Studio, Alpha Zoo, Research Delivery, Trust Layer, and Community sharing. - 2026-05-01 🔥 Correlation heatmap + OpenAI Codex OAuth + A-share pre-ST filter : New correlation dashboard/API computes rolling return correlations and renders an ECharts heatmap for portfolio and symbol analysis 64 https://github.com/HKUDS/Vibe-Trading/pull/64 . OpenAI Codex provider support now uses ChatGPT OAuth via vibe-trading provider login openai-codex , with Settings metadata and adapter regression tests 65 https://github.com/HKUDS/Vibe-Trading/pull/65 . Added and hardened the ashare-pre-st-filter skill for A-share ST/ ST risk screening, including Sina penalty relevance filtering so securities-account mentions do not inflate E2 counts 63 https://github.com/HKUDS/Vibe-Trading/pull/63 . - 2026-04-30 ⚙️ Web UI Settings + validation CLI hardening : New Settings page for LLM provider/model, base URL, reasoning effort, and data source credentials, backed by local/auth-protected settings APIs and data-driven provider metadata 57 https://github.com/HKUDS/Vibe-Trading/pull/57 . Also hardens python -m backtest.validation <run dir so missing, blank, malformed, non-existent, and non-directory inputs fail with clear operator-facing messages before validation starts 60 https://github.com/HKUDS/Vibe-Trading/pull/60 . - 2026-04-28 🚀 v0.1.6 released pip install -U vibe-trading-ai : Fixes vibe-trading --swarm-presets returning empty after pip install / uv tool install 55 https://github.com/HKUDS/Vibe-Trading/issues/55 — preset YAMLs now bundled inside the src.swarm package and pinned by a 6-test regression suite. Plus AKShare loader correctly routes ETFs 510300.SH and forex USDCNH to the right endpoints with hardened registry fallback. Rolls up everything since v0.1.5: benchmark comparison panel, /upload streaming + size limits, Futu loader HK + A-share , vnpy export skill, security hardening, frontend lazy loading 688KB → 262KB . - 2026-04-27 📊 Benchmark panel + upload safety : Backtest output now ships a benchmark comparison panel ticker / benchmark return / excess return / information ratio with yfinance-backed resolution for SPY, CSI 300, etc. 48 https://github.com/HKUDS/Vibe-Trading/issues/48 . Plus /upload streams the request body in 1 MB chunks and aborts past MAX UPLOAD SIZE , bounding memory under oversized/malformed clients 53 https://github.com/HKUDS/Vibe-Trading/pull/53 — pinned by a 4-case regression suite. - 2026-04-22 🛡️ Hardening + new integrations : Path containment enforced in safe path + journal/shadow tool sandbox, MANIFEST.in ships .env.example / tests / Docker files in sdist, route-level lazy loading shrinks frontend initial bundle 688KB → 262KB. Plus Futu data loader for HK & A-share equities 47 https://github.com/HKUDS/Vibe-Trading/pull/47 and vnpy CtaTemplate export skill 46 https://github.com/HKUDS/Vibe-Trading/pull/46 . - 2026-04-21 🛡️ Workspace + docs : Relative run dir normalized to active run dir 43 https://github.com/HKUDS/Vibe-Trading/pull/43 . README usage examples 45 https://github.com/HKUDS/Vibe-Trading/pull/45 . - 2026-04-20 🔌 Reasoning + Swarm : reasoning content preserved across all ChatOpenAI paths — Kimi / DeepSeek / Qwen thinking work end-to-end 39 https://github.com/HKUDS/Vibe-Trading/issues/39 . Swarm streaming + clean Ctrl+C 42 https://github.com/HKUDS/Vibe-Trading/issues/42 . - 2026-04-19 📦 v0.1.5 : Published to PyPI & ClawHub. python-multipart CVE floor bump, 5 new MCP tools wired analyze trade journal + 4 shadow-account tools , pattern recognition → pattern registry fix, Docker dep parity, SKILL manifest synced 22 MCP tools / 71 skills . - 2026-04-18 👥 Shadow Account : Extract your strategy rules from a broker journal → backtest the shadow across markets → 8-section HTML/PDF report showing exactly how much you leave on the table rule violations, early exits, missed signals, counterfactual trades . 4 new tools, 1 skill, 32 tools total. Trade Journal + Shadow Account samples now live in the web UI welcome screen. - 2026-04-17 📊 Trade Journal Analyzer + Universal File Reader : Upload broker exports 同花顺/东财/富途/generic CSV → auto trading profile holding days, win rate, PnL ratio, drawdown + 4 bias diagnostics disposition effect, overtrading, chasing momentum, anchoring . read document now dispatches PDF, Word, Excel, PowerPoint, images OCR , and 40+ text formats behind one unified call. - 2026-04-16 🧠 Agent Harness : Persistent cross-session memory, FTS5 session search, self-evolving skills full CRUD , 5-layer context compression, read/write tool batching. 27 tools, 107 new tests. - 2026-04-15 🤖 Z.ai + MiniMax : Z.ai provider 35 https://github.com/HKUDS/Vibe-Trading/pull/35 , MiniMax temperature fix + model update 33 https://github.com/HKUDS/Vibe-Trading/pull/33 . 13 providers. - 2026-04-14 🔧 MCP Stability : Fixed backtest tool Connection closed error on stdio transport 32 https://github.com/HKUDS/Vibe-Trading/pull/32 . - 2026-04-13 🌐 Cross-Market Composite Backtest : New CompositeEngine backtests mixed-market portfolios e.g. A-shares + crypto with shared capital pool and per-market rules. Also fixed swarm template variable fallback and frontend timeout. - 2026-04-12 🌍 Multi-Platform Export : /pine exports strategies to TradingView Pine Script v6 , TDX 通达信/同花顺/东方财富 , and MetaTrader 5 MQL5 in one command. - 2026-04-11 🛡️ Reliability & DX : vibe-trading init .env bootstrap 19 https://github.com/HKUDS/Vibe-Trading/pull/19 , preflight checks, runtime data-source fallback, hardened backtest engine. Multi-language README 21 https://github.com/HKUDS/Vibe-Trading/pull/21 . - 2026-04-10 📦 v0.1.4 : Docker fix 8 https://github.com/HKUDS/Vibe-Trading/issues/8 , web search MCP tool, 12 LLM providers, akshare / ccxt deps. Published to PyPI and ClawHub. - 2026-04-09 📊 Backtest Wave 2 : ChinaFutures, GlobalFutures, Forex, Options v2 engines. Monte Carlo, Bootstrap CI, Walk-Forward validation. - 2026-04-08 🔧 Multi-market backtest with per-market rules, Pine Script v6 export, 5 data sources with auto-fallback. Vibe-Trading is an open-source research workspace for turning finance questions into runnable analysis. It connects natural-language prompts to market-data loaders, strategy generation, backtest engines, reports, exports, and persistent research memory. It is designed for research, simulation, and backtesting — and, when you choose, autonomous trading through a broker you authorize yourself e.g. Robinhood Agentic Trading . It holds no funds and never trades outside the limits you set, and you can halt it instantly. | Task | Output | |---|---| Ask a trading question | Market research with tools, data, documents, and reusable session context. | Backtest a strategy idea | Strategy code, metrics, benchmark context, validation artifacts, and run cards. | Review your own trades | Broker-journal parsing, behavior diagnostics, rule extraction, and Shadow Account comparisons. | Improve repeated research | Persistent memory and editable skills turn useful routines into reusable workflows. | Run analyst teams | Multi-agent research reviews for investment, quant, crypto, macro, and risk workflows. | Ship usable artifacts | Reports, TradingView Pine Script, TDX, MetaTrader 5, MCP tools, and later research sessions. | Bench a pre-built alpha zoo | One-line IC + alive/reversed/dead categorisation across 456 alphas Qlib 158 + Kakushadze 101 + GTJA 191 + FF5 + Carhart on your universe. | pip install vibe-trading-ai Natural-language research vibe-trading run -p "Backtest a BTC-USDT 20/50 moving-average strategy for 2024, summarize return and drawdown, then export the report" Bench a pre-built alpha zoo one line vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025 --top 20 vibe-trading --upload trades export.csv vibe-trading run -p "Analyze my trading behavior, extract my shadow strategy, and compare it with my actual trades" Shadow Account starts from your own trading records instead of a generic strategy template. Upload a broker export, let the agent summarize your behavior, then compare the actual trading path with a rule-based shadow strategy. | Step | Agent output | |---|---| 1. Read your journal | Parses broker exports from 同花顺, 东方财富, 富途, and generic CSV formats. | 2. Profile your behavior | Holding days, win rate, PnL ratio, drawdown, disposition effect, overtrading, momentum chasing, and anchoring checks. | 3. Extract your rules | Turns recurring entries/exits into an explicit strategy profile instead of a hand-wavy summary. | 4. Run the shadow | Backtests the extracted rules and highlights rule breaks, early exits, missed signals, and alternative trade paths. | 5. Deliver the report | Produces an HTML/PDF report that can be inspected, archived, or refined in a later session. | vibe-trading --upload trades export.csv vibe-trading run -p "Analyze my trading behavior, extract my shadow strategy, and compare it with my actual trades" Most runs follow the same evidence path: route the request, load the right market context, execute tools, validate outputs, and keep the artifacts inspectable. | Layer | What happens | |---|---| Plan | Selects the relevant finance skills, tools, data sources, and swarm preset when useful. | Ground | Pulls A-shares, HK/US equities, crypto, futures, forex, documents, or web context through the available loaders. | Execute | Generates testable strategy code, runs tools, and uses the matching backtest engine or analysis workflow. | Validate | Adds metrics, benchmark comparison, Monte Carlo, Bootstrap, Walk-Forward, run cards, and warnings where applicable. | Deliver | Returns reports, artifacts, tool traces, and exports for TradingView, TDX, MetaTrader 5, MCP clients, or later sessions. | One get market data call, 18 market-data sources . Set source: "auto" — the loader picks by symbol, then walks a per-market chain ordered by IP-ban risk : never-banned public sources first, throttled / key-gated ones last. Zero config, no single point of failure. | Source | Markets | Auth | Role | |---|---|---|---| tencent · mootdx | A-share | none | never IP-banned mootdx = 通达信 TCP | eastmoney | A / US / HK | none | OHLCV + deep fundamentals & flow tools throttled | baostock · akshare | A + US/HK/futures/macro/fx | none | free fallbacks | tushare | A / futures / fund / macro | token | richest A-share | yahoo · sina · stooq | US /HK | none | direct chart/quotes/options · K-line to 1984 · EOD CSV | yfinance | US / HK | none | wrapper | finnhub · alphavantage · tiingo · fmp | US | key | optional providers | okx · ccxt | crypto | none | OKX + 100+ exchanges | futu | HK / A | OpenD | optional local FutuOpenD | local | any | none | your own CSV / Parquet / DuckDB via local: prefix | Fallback chains by IP-ban risk : A-share → tencent · mootdx · eastmoney · baostock · akshare · tushare · local US → yahoo · stooq · sina · eastmoney · yfinance · tiingo · fmp · finnhub · alphavantage · akshare · local HK → eastmoney · yahoo · futu · yfinance · akshare · local Crypto → okx · ccxt · yfinance · local · futures / fund / macro / forex → tushare / akshare → local Beyond OHLCV, 18 read-only data tools reach into fundamentals & flow — fund flow, dragon-tiger, northbound, margin, block trades, shareholder count, lockup, sector, research reports, news, SEC filings, financial statements, options chains, institutional holdings, market screening, symbol search, and macro — all exposed over MCP. An explicit local: symbol never silently falls back to a network source. Detailed inventories are folded below to keep the main README scannable. Open them when you want to inspect the available building blocks. Finance Skill Library 79 skills across 8 categories - 📊 79 specialized finance skills organized into 8 categories - 🌐 Complete coverage from traditional markets to crypto & DeFi - 🔬 Comprehensive capabilities spanning data sourcing to quantitative research | Category | Skills | Examples | |---|---|---| | Data Source | 9 | data-routing , tushare , yfinance , okx-market , akshare , mootdx , ccxt , eastmoney , sec-edgar | | Strategy | 17 | strategy-generate , cross-market-strategy , technical-basic , candlestick , ichimoku , elliott-wave , smc , multi-factor , ml-strategy | | Analysis | 17 | factor-research , macro-analysis , global-macro , valuation-model , earnings-forecast , credit-analysis , dividend-analysis | | Asset Class | 9 | options-strategy , options-advanced , convertible-bond , etf-analysis , asset-allocation , sector-rotation | | Crypto | 7 | perp-funding-basis , liquidation-heatmap , stablecoin-flow , defi-yield , onchain-analysis | | Flow | 7 | hk-connect-flow , us-etf-flow , edgar-sec-filings , financial-statement , adr-hshare | | Tool | 11 | backtest-diagnose , report-generate , pine-script , doc-reader , web-reader , vnpy-export , alpha-zoo | | Risk Analysis | 1 | ashare-pre-st-filter | Custom Data Source register your own historical OHLCV loader Need a market or vendor we don't ship a loader for? Add your own historical-bar loader and select it with source="<name " . The steps edit package source, so run from a clone pip install -e . . - Write the loader — create agent/backtest/loaders/<name loader.py with a class that satisfies DataLoaderProtocol duck-typed, no base class needed and is tagged with @register : python import pandas as pd from backtest.loaders.registry import register @register class DataLoader: name = "mysource" the value you pass as source= markets = {"us equity"} a share/us equity/hk equity/crypto/futures/fund/macro/forex requires auth = False def is available self - bool: return True token present? network reachable? def fetch self, codes, start date, end date, , interval="1D", fields=None : return {symbol: DataFrame indexed by trade date, columns: open, high, low, close, volume} ... - Register the module so @register fires — add "backtest.loaders.<name loader" to loader modules in agent/backtest/loaders/registry.py . - Allow the name through config validation — add "mysource" to VALID SOURCES in agent/backtest/runner.py . - Optional slot it into a market's FALLBACK CHAINS in registry.py so source="auto" can reach it. - Use it — source="mysource" in a backtest config, or via the CLI / agent. Real-time ticks / order-book depth are out of scope for loaders— the loader layer is point-in-time historical bars only. Live market data flows through the broker connectors instead: okx / binance / ccxt for crypto, futu / tiger for equities. Preset Trading Teams 29 swarm presets - 🏢 29 ready-to-use agent teams - ⚡ Pre-configured finance workflows - 🎯 Investment, trading & risk management presets | Preset | Workflow | |---|---| investment committee | Bull/bear debate → risk review → PM final call | global equities desk | A-share + HK/US + crypto researcher → global strategist | crypto trading desk | Funding/basis + liquidation + flow → risk manager | earnings research desk | Fundamental + revision + options → earnings strategist | macro rates fx desk | Rates + FX + commodity → macro PM | quant strategy desk | Screening + factor research → backtest → risk audit | technical analysis panel | Classic TA + Ichimoku + harmonic + Elliott + SMC → consensus | risk committee | Drawdown + tail risk + regime review → sign-off | global allocation committee | A-shares + crypto + HK/US → cross-market allocation | Plus 20+ additional specialist presets — run vibe-trading --swarm-presets to explore all. Alpha Zoo 456 pre-built quant alphas across 4 zoos - 🧬 456 cross-sectional alphas, lookahead-banned at the operator layer - 📈 IC + IR + alive/reversed/dead categorisation in one CLI command - 🔬 AST purity gate + 300-row lookahead sentinel test + pytest-socket network kill-switch - 📦 Apache-2 attribution for Qlib; per-zoo LICENSE.md declaring formulas as mathematical content - 🤝 Developer Certificate of Origin DCO sign-off workflow for community PRs | Zoo | Count | Source | License | |---|---|---|---| qlib158 | 154 | Microsoft Qlib Alpha158 Apache-2.0, commit-pinned | Apache-2.0 | alpha101 | 101 | Kakushadze 2015 , "101 Formulaic Alphas", arXiv:1601.00991 | Formulas are mathematical content | gtja191 | 191 | Guotai Junan 2014 , "191 Short-period Trading Alpha Factors" | Formulas are mathematical content | academic | 10 | Fama-French 5 + Carhart momentum + Jegadeesh reversal + George-Hwang 52-week-high + Amihud illiquidity + Harvey-Siddique skew price-based proxies | Public academic literature | Run vibe-trading alpha list to browse, vibe-trading alpha show <id for formulas + source, vibe-trading alpha bench --zoo X --universe Y --period Z to score a whole zoo. cli sm.mp4 | frontend sm.mp4 | ☝️ Natural-language backtest & multi-agent swarm debate — Web UI + CLI | pip install vibe-trading-ai Then run a first research task: vibe-trading init vibe-trading run -p "Backtest a BTC-USDT 20/50 moving-average strategy for 2024 and summarize return and drawdown" Upgrading from an older version?0.1.10 moved to LangChain 1.x. If imports break after pip install -U vibe-trading-ai over a pre-0.1.10 install e.g. langgraph fails to import , recreate the venv or run pip install --force-reinstall vibe-trading-ai . A fresh install is unaffected. Package name vs commands:The PyPI package is vibe-trading-ai . Once installed, you get three commands: Command Purpose vibe-trading Interactive CLI / TUI vibe-trading serve Launch FastAPI web server vibe-trading-mcp Start MCP server for Claude Desktop, OpenClaw, Cursor, etc. vibe-trading init interactive .env setup vibe-trading launch CLI vibe-trading serve --port 8899 launch web UI vibe-trading-mcp start MCP server stdio | Path | Best for | Time | |---|---|---| A. Docker | Try it now, zero local setup | 2 min | B. Local install | Development, full CLI access | 5 min | C. MCP plugin | Plug into your existing agent | 3 min | D. ClawHub | One command, no cloning | 1 min | - An LLM API key from any supported provider — or run locally with Ollama no key needed Python 3.11+ for Path B Docker for Path A- OpenAI Codex can also be used with ChatGPT OAuth: set LANGCHAIN PROVIDER=openai-codex , then run vibe-trading provider login openai-codex . This does not use OPENAI API KEY . Supported LLM providers:OpenRouter, OpenAI, DeepSeek, Gemini, Groq, DashScope/Qwen, Zhipu, Moonshot/Kimi, MiniMax, Xiaomi MIMO, Z.ai, Ollama local . See .env.example for config. Tip:All markets work without any API keys thanks to automatic fallback. yfinance HK/US , OKX crypto , mootdx A-shares, TCP-direct, no IP throttle , and AKShare A-shares, US, HK, futures, forex are all free. Tushare token is optional — mootdx is the preferred no-token A-share fallback, with AKShare as a broader backup. git clone https://github.com/HKUDS/Vibe-Trading.git cd Vibe-Trading cp agent/.env.example agent/.env Edit agent/.env — uncomment your LLM provider and set API key docker compose up --build Open http://localhost:8899 . Backend + frontend in one container. Docker publishes the backend on 127.0.0.1:8899 by default and runs the app as a non-root container user. If you intentionally expose the API beyond your own machine, set a strong API AUTH KEY and send Authorization: Bearer <key from clients. Note Using Ollama with Docker: the container reaches a host-side Ollama via host.docker.internal , not localhost inside the container localhost is the container itself . docker-compose.yml defaults OLLAMA BASE URL to http://host.docker.internal:11434 ; export OLLAMA BASE URL or set it in a top-level .env to point elsewhere. This relies on the host-gateway mapping in extra hosts , which requires Docker Engine ≥ 20.10 / Compose v2 provided automatically on Docker Desktop . Your data survives updates: persistent memory, the cross-session search index, user-created skills, shadow accounts, broker connector config, web sessions, backtest runs, swarm history, and uploads all live in named Docker volumes, so git pull && docker compose up --build keeps them. They are deleted only by docker compose down -v . git clone https://github.com/HKUDS/Vibe-Trading.git cd Vibe-Trading python -m venv .venv Activate source .venv/bin/activate Linux / macOS .venv\Scripts\Activate.ps1 Windows PowerShell pip install -e . cp agent/.env.example agent/.env Edit — set your LLM provider API key vibe-trading Launch interactive TUI Start web UI optional Terminal 1: API server vibe-trading serve --port 8899 Terminal 2: Frontend dev server cd frontend && npm install && npm run dev Open http://localhost:5899 . The frontend proxies API calls to localhost:8899 . Production mode single server : cd frontend && npm run build && cd .. vibe-trading serve --port 8899 FastAPI serves dist/ as static files NOTE vibe-trading serve binds 0.0.0.0 and is loopback-only by default: opening the UI on thesame machine http://localhost:8899 works with zero config. If you browse fromanother machine, a VM host, or a phone on your LAN, sensitive endpoints return 403 and the chat shows "Remote API access requires an API key" — set a strong API AUTH KEY in agent/.env , restart, and enter the same key once inSettings. Docker Desktop's host gateway: set VIBE TRADING TRUST DOCKER LOOPBACK=1 with the default 127.0.0.1 port bind. See MCP Plugin -mcp-plugin section below. npx clawhub@latest install vibe-trading --force The skill + MCP config is downloaded into your agent's skills directory. See ClawHub install -mcp-plugin for details. Copy agent/.env.example to agent/.env and uncomment the provider block you want. Each provider needs 3-4 variables: | Variable | Required | Description | |---|---|---| LANGCHAIN PROVIDER | Yes | Provider name openrouter , deepseek , groq , ollama , etc. | <PROVIDER API KEY | Yes | API key OPENROUTER API KEY , DEEPSEEK API KEY , etc. | <PROVIDER BASE URL | Yes | API endpoint URL | LANGCHAIN MODEL NAME | Yes | Model name e.g. deepseek-v4-pro | TUSHARE TOKEN | No | Tushare Pro token for A-share data falls back to AKShare | TIMEOUT SECONDS | No | LLM call timeout, default 120s | API AUTH KEY | Recommended for network deployments | Bearer token required when the API is reachable from non-local clients | VIBE TRADING ENABLE SHELL TOOLS | No | Explicit opt-in for shell-capable tools in remote API/MCP-SSE style deployments | VIBE TRADING ALLOWED FILE ROOTS | No | Extra comma-separated roots for document and broker-journal imports | VIBE TRADING ALLOWED RUN ROOTS | No | Extra comma-separated roots for generated-code run directories | CONTENT FILTER WARNING THRESHOLD | No | Content-filter warning ratio threshold default 0.05 = 5% . When the ratio of LLM responses blocked by content moderation exceeds this, the run card warns you to switch providers. | Ollama does not require an API key. OpenAI Codex uses ChatGPT OAuth and stores tokens via oauth-cli-kit, not in agent/.env. Free data no key needed : A-shares via AKShare, HK/US equities via yfinance, crypto via OKX, 100+ crypto exchanges via CCXT. The system automatically selects the best available source for each market. Vibe-Trading is a tool-heavy agent — skills, backtests, memory, and swarms all flow through tool calls. Model choice directly decides whether the agent uses its tools or fabricates answers from training data. | Tier | Examples | When to use | |---|---|---| Best | anthropic/claude-opus-4.7 , anthropic/claude-sonnet-4.6 , openai/gpt-5.5-pro , google/gemini-3.5-flash | Complex swarms 3+ agents , long research sessions, paper-grade analysis | Sweet spot default | deepseek-v4-pro , deepseek/deepseek-v4-pro , x-ai/grok-4.20 , z-ai/glm-5.1 , moonshotai/kimi-k2.6 , qwen/qwen3-max-thinking | Daily driver — reliable tool-calling at ~1/10 the cost | Avoid for agent use | -nano , -flash-lite , -coder-next , small / distilled variants | Tool-calling is unreliable — the agent will appear to "answer from memory" instead of loading skills or running backtests | The default agent/.env.example ships with DeepSeek official API + deepseek-v4-pro ; OpenRouter users can use deepseek/deepseek-v4-pro . The interactive TUI vibe-trading now uses a terminal-native transcript: a startup banner, prompt rule, previous-turn recap, live activity rail, Markdown/table rendering, and run timing all stay in the CLI. Non-interactive invocations such as vibe-trading run , pipes, and --json remain script-friendly. vibe-trading interactive TUI vibe-trading run -p "..." single run vibe-trading serve API server vibe-trading alpha list browse 456 pre-built alphas; show / bench / compare / export-manifest sub-commands available vibe-trading provider doctor print redacted provider/proxy/package diagnostics Slash commands inside TUI | Command | Description | |---|---| /help | Show all commands | /skills | List all 79 finance skills | /swarm | List 29 swarm team presets | /swarm run <preset vars json | Run a swarm team with live streaming | /swarm list | Swarm run history | /swarm show <run id | Swarm run details | /swarm cancel <run id | Cancel a running swarm | /list | Recent runs | /show <run id | Run details + metrics | /code <run id | Generated strategy code | /pine <run id | Export indicators TradingView + TDX + MT5 | /trace <run id | Full execution replay | /continue <run id <prompt | Continue a run with new instructions | /sessions | List chat sessions | /settings | Show runtime config | /clear | Clear screen | /quit | Exit | Single run & flags vibe-trading run -p "Backtest BTC-USDT MACD strategy, last 30 days" vibe-trading run -p "Analyze AAPL momentum" --json vibe-trading run -f strategy.txt echo "Backtest 000001.SZ RSI" | vibe-trading run vibe-trading -p "your prompt" vibe-trading --skills vibe-trading --swarm-presets vibe-trading --swarm-run investment committee '{"topic":"BTC outlook"}' vibe-trading --list vibe-trading --show <run id vibe-trading --code <run id vibe-trading --pine <run id Export indicators TradingView + TDX + MT5 vibe-trading --trace <run id vibe-trading --continue <run id "refine the strategy" vibe-trading --upload report.pdf vibe-trading alpha list --zoo gtja191 --limit 10 vibe-trading alpha show gtja191 171 vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025 --top 20 Moving average crossover on US equities vibe-trading run -p "Backtest a 20/50-day moving average crossover on AAPL for the past year, show Sharpe ratio and max drawdown" RSI mean-reversion on crypto vibe-trading run -p "Test RSI 14 mean-reversion on BTC-USDT: buy below 30, sell above 70, last 6 months" Multi-factor strategy on A-shares vibe-trading run -p "Backtest a momentum + value + quality multi-factor strategy on CSI 300 constituents over 2 years" After backtesting, export to TradingView / TDX / MetaTrader 5 vibe-trading --pine <run id Bench a pre-built alpha zoo one line : vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025 --top 20 Browse the catalogue and inspect a single alpha: vibe-trading alpha list --zoo gtja191 --theme reversal --limit 10 vibe-trading alpha show gtja191 171 Compose a multi-factor signal from the zoo Python : python from src.skills.multi factor.zoo signal engine import ZooSignalEngine engine = ZooSignalEngine.from zoo "gtja191 171", "gtja191 111", "gtja191 163" panel = ... your wide OHLCV panel signal = engine.compute signal panel Equity deep-dive vibe-trading run -p "Research NVDA: earnings trend, analyst consensus, option flow, and key risks for next quarter" Macro analysis vibe-trading run -p "Analyze the current Fed rate path, USD strength, and impact on EM equities and gold" Crypto on-chain vibe-trading run -p "Deep dive BTC on-chain: whale flows, exchange balances, miner activity, and funding rates" Bull/bear debate on a stock vibe-trading --swarm-run investment committee '{"topic": "Is TSLA a buy at current levels?"}' Quant strategy from screening to backtest vibe-trading --swarm-run quant strategy desk '{"universe": "S&P 500", "horizon": "3 months"}' Crypto desk: funding + liquidation + flow → risk manager vibe-trading --swarm-run crypto trading desk '{"asset": "ETH-USDT", "timeframe": "1w"}' Global macro portfolio allocation vibe-trading --swarm-run macro rates fx desk '{"focus": "Fed pivot impact on EM bonds"}' Save your preferences once vibe-trading run -p "Remember: I prefer RSI-based strategies, max 10% drawdown, hold period 5–20 days" The agent recalls them in future sessions automatically vibe-trading run -p "Build a crypto strategy that fits my risk profile" Analyze a broker export or earnings report vibe-trading --upload trades export.csv vibe-trading run -p "Profile my trading behavior and identify any biases" vibe-trading --upload NVDA Q1 earnings.pdf vibe-trading run -p "Summarize the key risks and beats/misses from this earnings report" vibe-trading serve --port 8899 | Method | Endpoint | Description | |---|---|---| GET | /runs | List runs | GET | /runs/{run id} | Run details | GET | /runs/{run id}/pine | Multi-platform indicator export | POST | /sessions | Create session | POST | /sessions/{id}/messages | Send message | GET | /sessions/{id}/events | SSE event stream | POST | /upload | Upload PDF/file | GET | /swarm/presets | List swarm presets | POST | /swarm/runs | Start swarm run | GET | /swarm/runs/{id}/events | Swarm SSE stream | GET | /alpha/list | List alphas filter by zoo/theme/universe | GET | /alpha/{alpha id} | Alpha metadata + source code | POST | /alpha/bench | Start a bench job returns job id | GET | /alpha/bench/{job id}/stream | SSE progress stream | GET | /settings/llm | Read Web UI LLM settings | PUT | /settings/llm | Update local LLM settings | GET | /settings/data-sources | Read local data source settings | PUT | /settings/data-sources | Update local data source settings | POST | /scheduled-runs | Create a scheduled research job interval-ms or cron | GET | /scheduled-runs | List scheduled jobs | DELETE | /scheduled-runs/{job id} | Cancel a scheduled job | Interactive docs: http://localhost:8899/docs For localhost development, vibe-trading serve keeps the browser workflow simple. For any non-local client, sensitive API endpoints require API AUTH KEY ; use Authorization: Bearer <key for JSON/upload requests. Browser EventSource streams are handled by the Web UI after you enter the same key once in Settings. Shell-capable tools are available to local CLI and trusted localhost workflows, but are not exposed to remote API sessions unless you explicitly set VIBE TRADING ENABLE SHELL TOOLS=1 . Document and journal readers are limited to upload/import roots by default; place files under agent/uploads , agent/runs , ./uploads , ./data , ~/.vibe-trading/uploads , or ~/.vibe-trading/imports , or add a dedicated directory through VIBE TRADING ALLOWED FILE ROOTS . The Web UI Settings page lets local users update the LLM provider/model, base URL, generation parameters, reasoning effort, and optional market data credentials such as the Tushare token. Settings are persisted to agent/.env ; provider defaults are loaded from agent/src/providers/llm providers.json . Settings reads are side-effect free: GET /settings/llm and GET /settings/data-sources never create agent/.env , and they only return project-relative paths. Settings reads and writes can expose credential state or update credentials/runtime environment, so they require API AUTH KEY when configured. If API AUTH KEY is unset for dev mode, settings access is accepted only from loopback clients. Run a research prompt or backtest on a repeating schedule. The background executor is off by default — start the server with VIBE TRADING ENABLE SCHEDULER=1 to enable it: VIBE TRADING ENABLE SCHEDULER=1 vibe-trading serve --port 8899 Then create jobs over REST. schedule is either a bare integer interval in milliseconds or a 5-field cron expression min hour dom mon dow : every 6 hours cron curl -X POST http://localhost:8899/scheduled-runs \ -H "Content-Type: application/json" \ -d '{"prompt":"Scan CSI300 for momentum breakouts and backtest the top 5","schedule":"0 /6 "}' list / cancel curl http://localhost:8899/scheduled-runs curl -X DELETE http://localhost:8899/scheduled-runs/<job id Each fire runs the prompt through a fresh agent session optional backtest parameters go in config , and jobs persist under ~/.vibe-trading/ so they survive restarts. Without the flag, the /scheduled-runs endpoints still record jobs but nothing fires. Add -H "Authorization: Bearer <key " to each call when API AUTH KEY is set. Vibe-Trading exposes 54 MCP tools for any MCP-compatible client. Runs as a stdio subprocess — no server setup needed. Core research tools work with zero API keys for HK/US/crypto; trading connector tools use the selected connector profile, and run swarm needs an LLM key. Claude Desktop Add to claude desktop config.json : { "mcpServers": { "vibe-trading": { "command": "vibe-trading-mcp" } } } OpenClaw Add to ~/.openclaw/config.yaml : skills: - name: vibe-trading command: vibe-trading-mcp For a first research-only smoke test, confirm tool discovery and run a market data or backtest request before selecting a trading connector profile. Core research tools can run without broker credentials; connector-backed trading tools should be used only after you intentionally select and check a connector profile. run swarm requires an LLM key. Cursor / Windsurf / other MCP clients vibe-trading-mcp stdio default vibe-trading-mcp --transport sse SSE for web clients MCP tools exposed 54 : list skills , load skill , start research goal , get research goal , add goal evidence , update research goal status , backtest , factor analysis , analyze options , pattern recognition , read url , read document , web search , write file , read file , trading connections , trading select connection , trading check , trading account , trading positions , trading orders , trading quote , trading history , list swarm presets , run swarm , get market data , get fund flow , get dragon tiger , get northbound flow , get margin trading , get block trades , get shareholder count , get lockup expiry , get sector info , get research reports , get stock news , get sec filings , get financial statements , get options chain , get stock profile , screen market , search symbol , get macro series , iwencai search , get swarm status , get run result , list runs , reap stale runs , retry run , analyze trade journal , extract shadow strategy , run shadow backtest , render shadow report , scan shadow signals . run swarm workers can call operator-approved tools from external MCP servers. Configure the server-side allowlist in VIBE TRADING SWARM AGENT CONFIG , ~/.vibe-trading/swarm-agent.json , or the fallback ~/.vibe-trading/agent.json ; then list remote tools in a swarm preset using the local MCP wrapper name, such as mcp internal kb search . Caller-provided variables stay template data only and cannot inject MCP URLs, commands, environment variables, or allowlist overrides. Install from ClawHub one command npx clawhub@latest install vibe-trading --force --force is required because the skill references external APIs, which triggers VirusTotal's automated scan. The code is fully open-source and safe to inspect. This downloads the skill + MCP config into your agent's skills directory. No cloning needed. Browse on ClawHub: clawhub.ai/skills/vibe-trading https://clawhub.ai/skills/vibe-trading OpenSpace — self-evolving skills All 79 finance skills are published on open-space.cloud https://open-space.cloud and evolve autonomously through OpenSpace's self-evolution engine. To use with OpenSpace, add both MCP servers to your agent config: { "mcpServers": { "openspace": { "command": "openspace-mcp", "toolTimeout": 600, "env": { "OPENSPACE HOST SKILL DIRS": "/path/to/vibe-trading/agent/src/skills", "OPENSPACE WORKSPACE": "/path/to/OpenSpace" } }, "vibe-trading": { "command": "vibe-trading-mcp" } } } OpenSpace will auto-discover all 79 skills, enabling auto-fix, auto-improve, and community sharing. Search for Vibe-Trading skills via search skills "finance backtest" in any OpenSpace-connected agent. This is the opposite direction from the MCP Plugin above.The MCP Plugin letsotheragents call Vibe-Trading tools. This section lets thebuilt-inVibe-Trading agent call tools fromyourexternal MCP servers. Create ~/.vibe-trading/agent.json : { "mcpServers": { "my-server": { "command": "uvx", "args": "my-mcp-server" } } } Run any CLI command — tools from ordinary external servers are automatically injected into the agent's registry after local tools: vibe-trading run "use my-server to do X" Vibe-Trading can connect directly to Interactive Brokers' official remote MCP endpoint in read-only mode. Add this to ~/.vibe-trading/agent.json : { "mcpServers": { "ibkr": { "type": "streamableHttp", "url": "https://api.ibkr.com/v1/api/mcp", "auth": { "type": "oauth", "scopes": "mcp.read" , "clientName": "Vibe-Trading", "cacheDir": "~/.vibe-trading/live/ibkr/oauth" }, "enabledTools": " " } } } Then start the browser OAuth flow: vibe-trading connector authorize ibkr-live-official-mcp-readonly The wildcard is accepted only for IBKR's mcp.read probe. Authorizing this profile confirms access to IBKR's official read scope; generic trading account and trading positions calls stay disabled until IBKR publishes stable read tool names that Vibe-Trading can map safely. A config that adds mcp.write must pin an explicit tool allowlist and still passes through the live order guard. If IBKR issues a pre-registered OAuth client, add clientId and clientSecret inside auth . For users who cannot wait for IBKR OAuth client approval, connect to a local TWS or IB Gateway session. Credentials stay inside IBKR's desktop app; Vibe- Trading only connects to 127.0.0.1 and exposes it as a connector profile. Install the optional SDK: pip install "vibe-trading-ai ibkr " Open TWS paper trading or IB Gateway paper, enable API socket clients, then run: vibe-trading connector list vibe-trading connector use ibkr-paper-local vibe-trading connector configure ibkr-paper-local --yes vibe-trading connector check vibe-trading connector account vibe-trading connector positions vibe-trading connector orders vibe-trading connector quote AAPL vibe-trading connector history AAPL --duration "30 D" --bar-size "1 day" Default local ports: | App | Paper | Live read-only | |---|---|---| | TWS | 7497 | 7496 | | IB Gateway | 4002 | 4001 | The agent exposes connector-scoped tools named trading connections , trading select connection , trading check , trading account , trading positions , trading orders , trading quote , and trading history . Live-broker raw MCP tools are not registered directly as mcp <broker . No IBKR order-placement tool is registered. | Field | Type | Default | Description | |---|---|---|---| type | string | inferred for stdio; required for HTTP | Omit for stdio, or set to sse / streamableHttp for URL-based servers. | command | string | required for stdio | Executable to spawn for stdio servers. Invalid for sse / streamableHttp servers. | args | array | | Command-line arguments for stdio servers only. | env | object | {} | Extra environment variables merged into the subprocess env for stdio servers only. | url | string | required for sse / streamableHttp | Remote SSE / streamable HTTP endpoint URL. Not used for stdio servers. | headers | object | {} | Extra HTTP headers for sse / streamableHttp servers only. | toolTimeout | number | 30 | Per-tool call timeout in seconds | initTimeout | number | unset max toolTimeout, 30 | MCP initialize / OAuth authorization timeout in seconds. Use this for slow browser authorization without widening ordinary tool calls. | enabledTools | array | " " | Tool allowlist. Use " " to expose all tools from the server | Config file location: ~/.vibe-trading/agent.json JSON or YAML . For URL-based transports, type is required. The agent no longer guesses between SSE and streamable HTTP from the URL suffix. When creating a session via the API you can pass mcpServers inside session.config to extend or override the global config for that session only: { "config": { "mcpServers": { "research-server": { "command": "uvx", "args": "research-mcp" , "enabledTools": "search", "fetch" } } } } Ordinary remote tools are exposed with stable names: mcp <server <tool . Live-broker MCP servers stay behind the trading connector surface. If two server names produce the same ASCII-safe local prefix e.g. foo-bar and foo bar both become foo bar , a deterministic hash suffix is appended at the server-segment level so names remain unique. The operator receives a warning: WARNING: Configured MCP server 'foo-bar' collides with another server after local name normalization. Using local tool prefix 'mcp foo bar <hash <tool ' to keep generated tool names unique. Rename the server in agent config if you want a different prefix. | Limit | Detail | |---|---| | Transport | stdio, SSE, and streamable HTTP | | Execution | serial only — MCP tools never enter the parallel readonly path | | Surfaces | tools only resources and prompts excluded in v1 | | Hot reload | not supported — restart the process to pick up config changes | | Swarm path | MCP tools are not available inside Swarm worker registries in v1 | Click to expand Vibe-Trading/ ├── agent/ Backend Python │ ├── cli/ CLI package — interactive TUI + subcommands │ ├── api server.py FastAPI server — runs, sessions, upload, swarm, SSE │ ├── mcp server.py MCP server — 54 tools for OpenClaw / Claude Desktop │ │ │ ├── src/ │ │ ├── agent/ ReAct agent core │ │ │ ├── loop.py 5-layer compression + read/write tool batching │ │ │ ├── context.py system prompt + auto-recall from persistent memory │ │ │ ├── skills.py skill loader 79 bundled + user-created via CRUD │ │ │ ├── tools.py tool base class + registry │ │ │ ├── memory.py lightweight workspace state per run │ │ │ ├── frontmatter.py shared YAML frontmatter parser │ │ │ └── trace.py execution trace writer │ │ │ │ │ ├── memory/ Cross-session persistent memory │ │ │ └── persistent.py file-based memory ~/.vibe-trading/memory/ │ │ │ │ │ ├── tools/ 68 auto-discovered agent tools │ │ │ ├── backtest tool.py run backtests │ │ │ ├── remember tool.py cross-session memory save/recall/forget │ │ │ ├── skill writer tool.py skill CRUD save/patch/delete/file │ │ │ ├── session search tool.py FTS5 cross-session search │ │ │ ├── swarm tool.py launch swarm teams │ │ │ ├── web search tool.py DuckDuckGo web search │ │ │ └── ... bash, file I/O, factor analysis, options, alpha browser + bench, etc. │ │ │ │ │ ├── factors/ Alpha Zoo — 456 alphas across 4 zoos │ │ │ ├── base.py 19 operators rank/scale/ts /delta/decay linear/safe div/vwap │ │ │ ├── registry.py AST-only metadata load + lazy compute + sanity gates │ │ │ ├── bench runner.py IC + alive/reversed/dead categorisation │ │ │ └── zoo/ qlib158 154 + alpha101 101 + gtja191 191 + academic 10 │ │ │ │ │ ├── api/ FastAPI route modules │ │ │ └── alpha routes.py /alpha/list, /alpha/{id}, /alpha/bench, SSE stream │ │ │ │ │ ├── skills/ 79 finance skills in 8 categories SKILL.md each │ │ ├── swarm/ Swarm DAG execution engine │ │ │ └── presets/ 29 swarm preset YAML definitions │ │ ├── session/ Multi-turn chat + FTS5 session search │ │ └── providers/ LLM provider abstraction │ │ │ └── backtest/ Backtest engines │ ├── engines/ 7 engines + composite cross-market engine + options portfolio │ ├── loaders/ 18 sources: tushare, okx, yfinance, akshare, baostock, tencent, mootdx, ccxt, futu, local, eastmoney, sina, stooq, yahoo, finnhub, alphavantage, tiingo, fmp │ │ ├── base.py DataLoader Protocol │ │ └── registry.py Registry + auto-fallback chains │ └── optimizers/ MVO, equal vol, max div, risk parity │ ├── frontend/ Web UI React 19 + Vite + TypeScript │ └── src/ │ ├── pages/ Home, Agent, AlphaZoo, RunDetail, Compare, Correlation, Settings │ ├── components/ chat, charts, layout │ └── stores/ Zustand state management │ ├── Dockerfile Multi-stage build ├── docker-compose.yml One-command deploy ├── pyproject.toml Package config + CLI entrypoint ├── tools/ Repo-level CI helpers │ └── ci grep gates.sh rejects yaml.load / trademark / per-stock-data leaks └── LICENSE MIT Vibe-Trading is part of the HKUDS agent ecosystem: | NanoBot | Ultra-Lightweight Personal AI Assistant AI-Trader Agent-Native Signal & Copy Trading Platform CLI-Anything Making All Software Agent-Native OpenSpace Self-Evolving AI Agent Skills ClawTeam Agent Swarm IntelligenceWe ship in phases. Items move to Issues when work begins. | Phase | Feature | Status | |---|---|---| Trust Layer | Reproducible run cards are emitted and shown in Run Detail; v1 adds tool traces and citations | v0 Shipped | Hypothesis Registry | Durable research hypotheses with lifecycle status, data sources, skills, run-card links, and invalidation notes | Backend MVP Shipped | Research Autopilot | Manual-first research loop: hypothesis → deterministic backtest → evidence report | Phase 1–3 Shipped | Data Bridge | Bring-your-own data: local CSV/Parquet/SQL connectors with schema mapping | Local loader Shipped | Options Lab | Vol surface, Greeks dashboard, payoff/scenario explorer | Planned | Portfolio Studio | Risk x-ray, constraints, turnover-aware optimizer, rebalance notes | Planned | Alpha Zoo | 452 pre-built alphas Qlib 158 + Kakushadze 101 + GTJA 191 + FF5 + Carhart with one-line bench, agent integration, and Web UI | Shipped 0.1.8 | Research Delivery | Scheduled briefs to Slack / Telegram / email-style channels | Scheduler Shipped | Community | Shareable skills, presets, and strategy cards | Exploring | We welcome contributions See CONTRIBUTING.md /HKUDS/Vibe-Trading/blob/main/CONTRIBUTING.md for guidelines. Good first issues are tagged with good first issue https://github.com/HKUDS/Vibe-Trading/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22 — pick one and get started. Want to contribute something bigger? Check the Roadmap -roadmap above and open an issue to discuss before starting. Thanks to everyone who has contributed to Vibe-Trading Recent v0.1.10 cycle contributors and credits: - @Hinotoi-agent — a security-hardening wave: local-shutdown auth 241 , loopback-host rebinding rejection 242 , agent shell-tool opt-in 243 , settings-write auth 245 , mandate proposal-id containment 256 , persistent-memory type validation 257 , and MCP swarm run-id containment 258 - @mvanhorn — the opt-in local data cache 177 , Gemini thoughtSignature round-trip over OpenAI-compat tool calls 176 , the custom data loader guide 194 , and the glm/zhipu provider alias + model-name inference 247 - @gyx09212214-prog — loader robustness for malformed crypto/RSSHub timeout env vars 227, 240 , requested yfinance end-date inclusion 226 , strict run-card JSON for non-finite metrics 238 , and ddgs retry-fallback coverage 239 - @BillDin — swarm agent status in the chat UI 188 , explicit preset-name handling 189 , the loader-backed market-data tool for swarm workers 199 , and preset-context continuations 200 - @Robin1987China — the Research Autopilot goal-hypothesis bridge 260 , the local CSV/Parquet/DuckDB data loader 252 , and an assistant-prefill fix + configurable Kimi User-Agent 248 - @LemonCANDY42 — the read-only runtime status dashboard 210 , persisted AgentLoop usage artifacts 223 , and opt-in Run Detail chart payloads 225 - @zwrong — the trace.jsonl overhaul with zero truncation + offload 206 and session-id on exit + resume <session-id 218 - @forge-builder — the AI contributor guide 173 and the OpenClaw MCP research-only smoke-test docs 165 - @skloxo — Chinese zh-CN frontend localization adopted from 217 - @LeeCQiang — Chinese docstrings across all 452 Alpha Zoo factors 180 - @KaiLuettmann — GHCR pre-built image publishing on release 187 - @ngoanpv — Gemini thought signature preservation through the AgentLoop dict path 184 - @ShahNewazKhan — Docker host-Ollama reachability via host.docker.internal 196 - @sambazhu — frontend sync of completed chat attempts 236 - @bhlt — baostock-native code format support 230 - @octo-patch — MiniMax M3 default model upgrade 162 - @warren618 / Haozhe Wu — the global data layer 8 sources + 18 read-only data tools , the 10 broker SDK connectors, the alpha-compare full stack, the provider-reliability overhaul, multi-engine web search fallback, responsive Stop + SSE reconnect, and release integration Vibe-Trading is research and trading software. It is not investment advice, holds no funds, and runs no execution venue. Trading through a broker channel you explicitly authorize e.g. Robinhood Agentic Trading happens only within the limits you set and which you can halt at any time. This broker-trading capability is experimental and not verified by us against a real broker account — use it at your own risk. Past performance does not guarantee future results. MIT License — see LICENSE /HKUDS/Vibe-Trading/blob/main/LICENSE ⭐ If Vibe-Trading helps your research, a star helps more people find it. Thanks for visiting Vibe-Trading ✨