Show HN: Halis Code – Agent Coding

Halis Code, a new coding agent released by developer binhdzs1tg on GitHub, ships as both a terminal tool (installed via `npm install -g halis-code`, requiring Node 20 or newer) and a desktop app with installers for macOS arm64 and x64, Linux (.deb/.AppImage) and Windows (NSIS .exe), the desktop build currently unsigned. The agent targets long-session failures with compaction at safe cut points that never split a tool call from its result, a repeat guard that escalates reminders at 3, 5 and 8 identical canonicalized calls and hard-stops at 12, self-explaining approvals before risky shell commands, and oversized tool output spilled to a file with a preview rather than truncated. The tool adds slash commands including `/compact`, `/diff`, `/usage`, `/yolo` to toggle command approvals off, and `/init` to write an `AGENTS.md` for the current repo.

A coding agent with guardrails — one agent, two faces: your terminal and your desktop. Halis Code streams an agent that reads, edits and runs code in your project — and keeps its own context honest while it does: compaction before the window fills, approvals before anything destructive runs, a repeat guard against loops, and nothing ever lost to silent truncation. Install install · Terminal ui the-terminal-ui · Desktop app the-desktop-app · Docs documentation Because most of them are either a terminal tool or a desktop app, and the interesting failures happen in the long sessions: context that fills up and quietly degrades, the same failing tool call repeated eleven times, a docker compose output eating the whole window. Halis Code treats those as the product: - Compaction with safe cut points — when the transcript crosses the token budget, older history folds into a model-written summary. The cut never splits a tool call from its result, and a verbatim tail keeps the current task intact. - A repeat guard — identical calls canonicalized, so argument order cannot hide a repeat earn escalating reminders at 3, 5 and 8, and a hard stop at 12. - Approvals that explain themselves — every risky shell command asks first, with the reason on the card: "it deletes files recursively or by force", "it pipes command output into a shell", … - Spill, not truncation — oversized tool output lands in a readable file with a preview and a pointer, so nothing disappears and nothing bloats the context. Terminal node 20 or newer : npm install -g halis-code halis Desktop — grab the installer for your platform from the releases page https://github.com/binhdzs1tg/halis-code/releases : .dmg macOS arm64 + x64 , .deb / .AppImage Linux , or the NSIS .exe setup Windows . The desktop app is unsigned for now — on macOS that means the usual right-click → open on first launch. From source : git clone https://github.com/binhdzs1tg/halis-code.git cd halis-code npm install npm run dev:cli terminal ui, watch mode npm run dev:desktop build + launch the desktop app halis opens a session that behaves like a terminal-first pair programmer: a bordered composer with a command palette, a live spinner while the model thinks, tool cards with durations and output previews, bash approvals before anything destructive runs, and a status line with model, context usage and session cost straight from the catalog. The mascot — the Halis penguin — sits on the welcome screen, redrawn pixel by pixel in truecolor half-blocks. A few ways in: halis interactive session halis "fix the failing build" start with a prompt halis -p "summarize this repo" answer once, then exit halis -p --json "run the tests" one event per line, for scripts halis -c continue the last session here halis sessions list stored sessions halis mascot the penguin, full size Slash commands inside a session: | command | what it does | |---|---| | /help | list every command | | /model | pick a model from the catalog search + variants | | /models | the same picker, alias | | /provider | switch provider preset zai, deepseek, groq, … | | /diff | git diff of the working tree | | /compact | compact the transcript now | | /resume | pick an earlier session to load | | /title | rename this session auto-titled after turn one | | /export | write the transcript to markdown | | /usage | token totals and estimated cost | | /skills | list installed skills | | /yolo | toggle command approvals off careful | | /doctor | check config, key, catalog and endpoint | | /init | write an AGENTS.md for the current repo | | /status | config, key and session info | | /mascot | say hi to the penguin | | /clear | drop the conversation context | | /exit | quit or ctrl+c twice | Type command to run something in your own shell, without the model in the middle. The whole models.dev https://models.dev catalog ships in the box: 200+ providers and 8,000+ models, bundled as a snapshot so model picking works offline and refreshed in the background with ETag-cached revalidation. Both wire protocols are supported — OpenAI-style chat completions for most providers, Anthropic messages with thinking blocks for the Anthropic family — chosen from catalog data instead of a hand-listed table. halis -m anthropic/claude-sonnet-4-5 high provider/model plus reasoning variant halis -m glm-4.7-flash bare ids search the favorites first halis --yolo "run the whole migration" no approval prompts Keys come from each provider's documented environment variable ANTHROPIC API KEY , DEEPSEEK API KEY , ZAI API KEY , … or plain HALIS API KEY ; HALIS BASE URL + HALIS MODEL reach anything self-hosted, and the classic presets zai , deepseek , moonshot , groq , openai , openrouter , ollama work through /provider . Without a key the cli runs in a clearly labeled demo mode, so the interface stays explorable. The agent's toolkit: ls , read , write , edit , glob , grep , bash with run in background and timeout promotion to background jobs , job output / job kill , web fetch refuses private addresses , web search keyless, DuckDuckGo-backed , todo write the plan card , skill progressive-disclosure skills from .halis/skills/ /SKILL.md , ask user and task a subagent that explores with its own context and reports back . Developing without a key works too — a scripted OpenAI-compatible provider ships with the cli, and the ci pipeline runs the whole agent loop against it for every push: npm run mock -w halis-code listens on :8787 HALIS BASE URL=http://localhost:8787/v1 HALIS API KEY=mock \ node packages/cli/bin/halis.js The Electron app pairs a session-list sidebar and a centered conversation with a workspace rail — files, search, editor, terminal. The same guardrails ride along, plus desktop-only machinery: the mcp client, subagents, skill loading, patch application, and a provider key vault behind Electron safeStorage . - Streaming agent with live tool cards, plan todos and a message queue while a run is in flight. - Workspace rail — explorer create, rename, delete , editor with tabs and save, terminal panel, and search across the workspace. - Model catalog with variants, a key dialog, settings, focus mode, dark theme, auto-titled sessions with history. All twenty screenshots live in apps/desktop/docs/screenshots https://github.com/binhdzs1tg/halis-code/blob/main/apps/desktop/docs/screenshots . The same code runs on macOS, Linux and Windows, and the ci matrix tests all three on every push: - Shell — commands go through the user's login shell on unix $SHELL , falling back to the account shell, then /bin/bash and through cmd.exe on Windows. Set HALIS SHELL to force one — a posix-style bash.exe git bash is invoked with -c , pwsh.exe with -NoProfile -NonInteractive -Command , anything else must speak cmd. The system prompt tells the model which shell it has, so on Windows it writes dir and %VAR% instead of ls and $VAR . - Process trees — timeouts and cancels kill the whole tree process groups with SIGTERM-to-SIGKILL escalation on unix, taskkill /T on Windows , and a foreground command that outlives its timeout is promoted to a background job on every platform. - Files — read shows CRLF files without the carriage returns, edit folds replacements into the line endings the file already uses, and glob matching follows the filesystem: case-insensitive on Windows and macOS, strict on Linux. | doc | what it covers | |---|---| | docs/architecture.md https://github.com/binhdzs1tg/halis-code/blob/main/docs/architecture.md | how the pieces fit, and why | | docs/development.md https://github.com/binhdzs1tg/halis-code/blob/main/docs/development.md | commands, smoke suites, adding tools, env vars | | docs/releases.md https://github.com/binhdzs1tg/halis-code/blob/main/docs/releases.md | how a tag becomes installers and an npm package | | docs/security.md https://github.com/binhdzs1tg/halis-code/blob/main/docs/security.md | the guardrails as a system — trust boundaries and all | | CHANGELOG.md https://github.com/binhdzs1tg/halis-code/blob/main/CHANGELOG.md | what shipped, when | | CONTRIBUTING.md https://github.com/binhdzs1tg/halis-code/blob/main/CONTRIBUTING.md | the short path to a merged pull request | | SECURITY.md https://github.com/binhdzs1tg/halis-code/blob/main/SECURITY.md | reporting a vulnerability, scope | TypeScript 7 everywhere, strict. From the root: npm run typecheck all workspaces npm run build cli bundles core from source , then desktop npm run dev:cli watch mode for the terminal ui npm run dev:desktop build + launch the desktop app npm run smoke -w @halis/core the terminal-side loop against a scripted provider npm run smoke -w @halis/desktop algorithm smoke tests npm run lint:md markdownlint over every md file The everyday details — smoke suite internals, the mock provider, every environment variable — are in docs/development.md https://github.com/binhdzs1tg/halis-code/blob/main/docs/development.md . Conventions for humans and coding agents live in AGENTS.md https://github.com/binhdzs1tg/halis-code/blob/main/AGENTS.md . Cutting a release is one step: push a semver tag v0.3.0 . The release assembles itself — notes grouped from the commit log, installers built on all three platforms, the npm package published with provenance. The full pipeline is in docs/releases.md https://github.com/binhdzs1tg/halis-code/blob/main/docs/releases.md . Guardrails are the product, so they are documented like one: docs/security.md https://github.com/binhdzs1tg/halis-code/blob/main/docs/security.md explains the trust boundaries approvals, the fetch guard, the hostile-renderer discipline, process trees , and SECURITY.md https://github.com/binhdzs1tg/halis-code/blob/main/SECURITY.md explains how to report a hole in any of them — privately, please. Pull requests are welcome — CONTRIBUTING.md https://github.com/binhdzs1tg/halis-code/blob/main/CONTRIBUTING.md is the short path, and the ci matrix will keep you honest on all three platforms. MIT licensed; see LICENSE https://github.com/binhdzs1tg/halis-code/blob/main/LICENSE . The model catalog comes from models.dev https://models.dev — this repo just ships the snapshot and the picker around it. The terminal ui is built on Ink https://github.com/vadimdemedes/ink-react and React, the desktop app on Electron, and everything compiles with TypeScript 7 in strict mode.