# Use your favorite coding agent with any model > Source: > Published: 2026-08-20 11:14:55+00:00 ### Add a key Run bare to open the interactive picker, or pass flags for a non-interactive add. ``` # OpenRouter, Vercel AI Gateway, # OpenCode Go, DeepSeek, Cloudflare, # Google AI Studio, Kilo Gateway, # Amazon Bedrock, # OAuth: Codex, SuperGrok, GitHub Copilot, Cursor # Local: Ollama, LM Studio, llama.cpp # more... aivo keys add Copied! ``` Manage API keys. Launch coding agents with the provider and model you want. Or work directly in the built-in Aivo Code. A single binary for macOS, Linux, WSL, and Windows. Choose the method that fits your system. ``` curl -fsSL https://getaivo.dev/install.sh | bash Copied! irm https://getaivo.dev/install.ps1 | iex Copied! brew install yuanchuan/tap/aivo Copied! ``` Add API keys from any provider you **trust**. Keys are encrypted and stored locally, so you can manage them and switch anytime. Run bare to open the interactive picker, or pass flags for a non-interactive add. ␃WPNCODE7␃ Move keys between machines through a single password-encrypted file. ``` # prompts for a password aivo keys export ~/keys.bak # same password on the other machine, or pass a URL aivo keys import ~/keys.bak aivo keys import https://example.com/keys.bak # non-interactive (CI / scripts) aivo keys export ~/keys.bak --password-stdin <<< "my secret" Copied! ``` List, activate, inspect, edit, ping, and re-auth saved keys. ``` # list all saved keys aivo keys # quickly add a key with options aivo keys add --base-url https://openrouter.ai/api --key sk-xxx # activate a key to use aivo keys use aivo keys use mykey # print saved data of a key aivo keys cat # edit a saved key aivo keys edit # health-check aivo keys ping # OAuth re-login / rotate a key aivo keys reauth # for more options aivo keys --help Copied! ``` Launch a coding agent with any provider or model you want. All extra arguments are passed through to the underlying tool. ``` aivo claude Copied! ``` Use a saved API key with `-k` , or omit the value to open the key picker. Pass `-k` alone with `-m` to pick both at once. ``` aivo claude -k openrouter aivo claude -k copilot aivo claude -k Copied! ``` Pin a model with `-m` , or omit the value to open the model picker. Once a model is applied, `aivo claude` remembers it for the next run. ``` aivo claude -m moonshotai/kimi-k2.5 aivo claude -m Copied! ``` **Per-slot models** Claude Code runs multiple models in a single session, `haiku` /`sonnet` /`opus` /`fable` slots plus a subagent override. Pin each slot to a different model, or pass a slot flag without a value to open the picker for that slot. ``` aivo claude --sonnet-model deepseek-v4-pro --haiku-model deepseek-v4-flash aivo claude --fable-model gpt-5.4 --subagent-model claude-haiku-4-5 # open the picker for one slot aivo claude --opus-model Copied! aivo codex Copied! ``` Use a saved API key with `-k` , or omit the value to open the picker. ``` aivo codex -k vercel aivo codex -k Copied! ``` Pin a model with `-m` , or omit the value to open the model picker. ``` aivo codex -m xiaomi/mimo-v2-pro aivo codex -m Copied! ``` **Per-slot models** Codex runs multiple models in a single session, the main model plus `review` and `subagent` overrides. Pin each slot to a different model, or pass a slot flag without a value to open the picker for that slot. ``` aivo codex --review-model gpt-5.3-codex --subagent-model claude-haiku-4-5 # open the picker for one slot aivo codex --review-model Copied! ``` **Codex desktop app (experimental)** Launch the native Codex with the same backend. The app's in-app model picker only shows names starting with `gpt-` or `claude-` ; other models still work, but won't appear there. ``` aivo codex-app aivo codex-app -k Copied! aivo pi Copied! ``` Use a saved API key with `-k` , or omit the value to open the picker. ``` aivo pi -k cursor aivo pi -k Copied! ``` Pin a model with `-m` , or omit the value to open the model picker. ``` aivo pi -m composer-2.5 aivo pi -m Copied! ``` **Transparent mode** Because Pi supports multiple upstream protocols, by default aivo puts its local router in the middle and normalizes the stream. Use `--transparent` to hand Pi the URL and the right API type so it talks to the provider directly. ``` aivo pi --transparent -k openrouter Copied! aivo grok Copied! ``` Use a saved API key with `-k` , or omit the value to open the picker. ``` aivo grok -k openrouter aivo grok -k Copied! ``` Pin a model with `-m` , or omit the value to open the model picker. ``` aivo grok -m gpt-5.4 aivo grok -m Copied! aivo gemini Copied! ``` Use a saved API key with `-k` , or omit the value to open the picker. ``` aivo gemini -k google aivo gemini -k Copied! ``` Pin a model with `-m` , or omit the value to open the model picker. ``` aivo gemini -m gemini-2.5-pro aivo gemini -m Copied! aivo opencode Copied! ``` Use a saved API key with `-k` , or omit the value to open the picker. ``` aivo opencode -k openrouter aivo opencode -k Copied! ``` Pin a model with `-m` , or omit the value to open the model picker. ``` aivo opencode -m z-ai/glm-4.7 aivo opencode -m Copied! ``` **Install the plugin first** Amp support ships as a separate plugin. Install it once, then run it like any other agent. ``` aivo plugins install github:yuanchuan/aivo-amp aivo amp Copied! ``` Use a saved API key with `-k` , or omit the value to open the picker. ``` aivo amp -k openrouter aivo amp -k Copied! ``` Pin a model with `-m` , or omit the value to open the model picker. ``` aivo amp -m gpt-5.4 aivo amp -m Copied! ``` **Per-mode models** Amp routes between `rush` , `smart` , `deep` , and `large` modes. Pin each mode to a different model, or pass a mode flag without a value to open the picker for that mode. ``` aivo amp --smart-model claude-sonnet-4.6 --rush-model claude-haiku-4-5 aivo amp --deep-model gpt-5.4-thinking --large-model deepseek-v4-pro # pin the starting mode, or omit the value to open the mode picker aivo amp --mode deep aivo amp --mode Copied! ``` **Install the plugin first** omp support ships as a separate plugin. Install it once, then run it like any other agent. ``` aivo plugins install github:yuanchuan/aivo-omp aivo omp Copied! ``` Use a saved API key with `-k` , or omit the value to open the picker. ``` aivo omp -k openrouter aivo omp -k Copied! ``` Pin a model with `-m` , or omit the value to open the model picker. ``` aivo omp -m deepseek-v4-pro aivo omp -m Copied! ``` **Install the plugin first** GitHub Copilot CLI support ships as a separate plugin. Install it once, then run it like any other agent. ``` aivo plugins install github:yuanchuan/aivo-copilot aivo copilot Copied! ``` Use a saved API key with `-k` , or omit the value to open the picker. ``` aivo copilot -k openrouter aivo copilot -k Copied! ``` Pin a model with `-m` , or omit the value to open the model picker. ``` aivo copilot -m claude-sonnet-4.6 aivo copilot -m Copied! ``` Without a tool name, `aivo run` opens an interactive picker of agents and plugins, with your last choice selected by default. ``` aivo run Copied! ``` Pin a coding agent and its usual flags under one name, then launch the whole thing with `aivo ` (or the long form, `aivo run ` ). Inline flags at run time override the saved ones, handy for locking in the per-slot model setups you'd otherwise retype every session. ``` # Claude Code with separate models per slot aivo alias work claude -k openrouter \ --opus-model deepseek/deepseek-v4-pro \ --sonnet-model deepseek/deepseek-v4-flash \ --haiku-model deepseek/deepseek-v4-flash \ # Amp with separate models per mode, pinned to deep mode aivo alias task amp -k openrouter \ --smart-model openai/gpt-5.5 \ --deep-model anthropic/claude-opus-4.7 \ --rush-model openai/gpt-5.4 \ --large-model deepseek/deepseek-v4-pro # run them aivo work aivo task Copied! ``` `aivo code` is the built-in coding agent in your terminal. It works with any model you've added, from a frontier API to a local GGUF, and extends with skills, MCP servers, and subagents. `/plan` , `/goal` , `/review` , `/rewind` , `/config` , and more. `--share` or `/share` . Start the TUI, pick a key, resume a prior session, or live-share it. ``` aivo code # open the key picker aivo code -k # resume a saved session aivo code --resume aivo code --resume last # live-share the session to a viewer URL aivo code --share Copied! ``` Queue text files or images for the agent to read. Pass `--attach` as many times as you need, or paste an image straight from the clipboard with `Ctrl+V` in the session. ``` aivo code --attach README.md aivo code --attach README.md --attach screenshot.png Copied! ``` Send one prompt and exit with a plain reply — no tools. The shortcut is a bare quoted string: `aivo "..."` rewrites to `aivo code -p "..."` . Use `-p` /`--prompt` when you also want flags. ``` aivo "pro tips for git" aivo -p "pro tips for git" -m gpt-5.4 # type interactively, Ctrl-D to send aivo -p Copied! ``` Pipe anything into aivo. It reads stdin, adds your prompt, and sends it to the model. ``` git diff | aivo -p "Write a commit message" cat error.log | aivo -p "Find the root cause" cat error.log | aivo -p Copied! ``` Once you add a provider and set up the key, you can use the `models` command to see the available models the provider offers. Most providers provide the model list through API, so aivo fetches it on demand and caches it for later use. Fetches the active key's model list (cached). Filter with `-s` , or pick another key with `-k` . ``` # active key's models, or pick one aivo models aivo models -k openrouter # filter by name aivo models -s free aivo models -k openrouter -s claude # force refresh the cached list aivo models --refresh Copied! ``` `--json` prints aivo's normalized catalog for scripts — not the raw upstream payload. Pipe to `jq` to explore and filter. ``` aivo models --json aivo models -k openrouter --json | jq Copied! ``` If a model name is too long, you can give it a short alias. Model aliases are accepted anywhere `-m` /`--model` works. ``` aivo alias fast=claude-haiku-4-5 aivo alias mimo xiaomi/mimo-v2-pro # use it aivo claude -m fast aivo code -k vercel -m mimo # list and remove aivo alias aivo alias rm fast Copied! ``` Run any open-weight GGUF from a Hugging Face repo or a local `.gguf` file. The `hf:` prefix, full HF URLs, and plain file paths work anywhere a model name does — in `aivo code` , an agent's `-m` , or the bare `aivo` shortcut. Point `aivo` , `aivo code` , or an agent's `-m` at a repo or a local `.gguf` file. The first reference caches the model and starts a local server. ``` aivo hf:Qwen/Qwen2.5-0.5B-Instruct-GGUF aivo https://huggingface.co/allenai/Olmo-3-1025-7B # a local .gguf works too aivo code -m ./Qwen2.5-0.5B-Instruct-Q4_K_M.gguf Copied! ``` GGUF repos usually publish several quantizations. Append `:` (e.g. `Q5_K_M` , `Q4_K_M` ) to pick a specific file; if you don't, aivo defaults to `Q4_K_M` (or the closest available). ``` aivo code -m hf:bartowski/Llama-3.2-3B-Instruct-GGUF:Q5_K_M aivo claude -m hf:bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M Copied! ``` aivo picks sane defaults for the bundled `llama-server` . Set these env vars to override them. ``` AIVO_LLAMA_CTX=16384 # smaller context on a low-RAM machine AIVO_LLAMA_NGL=20 # GPU layers (AIVO_GPU=cpu to stay on CPU) AIVO_LLAMA_ARGS='--temp 0.1' # extra llama-server flags AIVO_LLAMA_MMPROJ=off # skip the vision projector AIVO_LLAMA_DRAFT=off # skip the draft model Copied! ``` Pass `hf:` wherever `-m` /`--model` is accepted. Combine with per-slot flags for Claude Code and Amp to mix local and remote models in the same session. ``` aivo claude -m hf:Qwen/Qwen2.5-0.5B-Instruct-GGUF aivo pi -m hf:Qwen/Qwen2.5-0.5B-Instruct-GGUF # mix: remote opus, local sonnet aivo claude \ --opus-model claude-opus-4.7 \ --sonnet-model hf:Qwen/Qwen2.5-0.5B-Instruct-GGUF Copied! ``` A bare `hf:` opens a picker over the local cache — useful once you've pulled a few models and don't want to retype the repo path. ``` aivo code hf: aivo claude hf: Copied! ``` `aivo hf` lists the cached repos; `--verbose` expands each repo to show every downloaded quant. The rest are housekeeping commands. ``` # list cached repos aivo hf # pre-pull a model (handy before going offline) aivo hf pull hf:Qwen/Qwen2.5-0.5B-Instruct-GGUF # delete one quant or a whole repo aivo hf rm --quant Q5_K_M aivo hf rm --all -y # wipe the whole cache aivo hf clean -y Copied! ``` Expose your active provider as a local OpenAI-compatible endpoint. Any tool that speaks the OpenAI API can use it, VS Code extensions, Python scripts, anything. Listen on localhost by default. Change port/host when you need LAN or a different bind. ``` aivo serve aivo serve --port 8080 aivo serve --host 0.0.0.0 Copied! ``` If a request hits a rate limit (429) or server error (5xx), aivo retries with the next saved key automatically. ``` aivo serve --failover Copied! ``` Log every request and response. Pipe to `jq` for readable output, or write to a file. ``` aivo serve --log | jq . aivo serve --log /tmp/requests.jsonl Copied! ``` Require a token for clients, enable CORS for browser tools, or tighten the upstream timeout. ``` aivo serve --auth-token aivo serve --auth-token my-secret aivo serve --cors aivo serve --timeout 60 Copied! ``` Point any OpenAI-compatible client at the local endpoint — curl works as a quick sanity check. ``` curl http://127.0.0.1:24860/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "hello"}]}' Copied! ``` One feed across aivo's own events (code, run, serve), native CLI sessions (claude, codex, gemini, pi, opencode), and amp threads, read from each tool's on-disk session files and aivo's local SQLite. Scoped to the current project by default. Newest first in the current project. Pass `--all` to include every project on this machine. ``` # recent activity in the current project aivo logs # every project on this machine aivo logs --all Copied! ``` Narrow by source, model, key, time, or text. `--errors` shows only failures. ``` aivo logs --by code -n 5 aivo logs --by claude --errors aivo logs --by native aivo logs --model glm-4.7 aivo logs -s "rate limit" aivo logs --since 24h aivo logs --json Copied! ``` Publish a session via a tunneled viewer URL, useful for showing a teammate a bug repro, an agent transcript, or an interesting model run. The server is just a bridge, it forwards viewer requests to your machine over the tunnel and keeps no copy of the session. ``` # pick a session in the current project aivo logs share # share a specific row by id prefix aivo logs share 1335c631 # pick from every project on this machine aivo logs share --all # follow updates and open in the browser aivo logs share --open # skip redaction (be sure) aivo logs share --no-redact Copied! ``` Aggregates token counts from aivo code, Claude Code, Codex, Gemini, OpenCode, Amp, and Pi by reading each tool's native data files. ``` aivo stats aivo stats claude aivo stats code Copied! ``` Raw numbers, provider filters, time windows, and cache bypass for scripting. ``` # raw numbers for scripts aivo stats -n # filter by provider aivo stats -s openrouter # last N units (m, h, d, w) aivo stats --since 7d aivo stats claude --since 24h # show all models aivo stats -a # bypass cache aivo stats -r Copied! ``` What a typical `aivo stats` summary looks like. ``` bash $ aivo stats ──────────────────────────────────────────────────── 408M tokens · 14B cached · 5.0K sessions · 77 models By tool sessions tokens claude 4.2K 295M ████████████████████ codex 256 87M █████▉ opencode 166 10M ▊ code 91 8.0M ▌ gemini 204 4.2M ▎ pi 85 3.8M ▎ By model tokens gpt-5.4 75M ████████████████████ minimax-m2.5 63M ████████████████▊ claude-sonnet-4.6 53M ██████████████▏ claude-opus-4.6 40M ██████████▋ minimax-m2.7 38M ██████████▏ claude-opus-4.7 31M ████████▏ laguna-xs-2.1 22M █████▉ claude-haiku-4-5-20251001 14M ███▉ kimi-k2.5:cloud 11M ██▉ claude-sonnet-4.5 6.6M █▊ gpt-5.3-codex 6.1M █▋ glm-4.7-free 6.0M █▋ glm-4.7 5.0M █▍ mercury-2 4.3M █▏ deepseek-v4-flash 3.7M █ gpt-5.5 3.6M █ kimi-k2.5 2.0M ▌ starter 1.8M ▌ gpt-5.1-codex 1.5M ▍ kat-coder-pro-v1 1.4M ▍ others (57 models) 9.8M ██▋ Copied! ``` Try aivo without setting up a provider first. `aivo-starter` bundles a couple of models **for learning and testing**, enough to feel how aivo works before you bring your own key. `aivo/starter` DeepSeek V4 Flash · official API A general-purpose default for everyday tasks. `poolside/laguna-s-2.1` Laguna S 2.1 · Once aivo is installed, you can use it straight away. ``` aivo "tell me a short story" aivo code Copied! ``` Link your device to an account for higher daily limits on the starter pool. ``` aivo account login aivo account usage Copied! ``` The starter pool has a finite daily budget, intended for interactive coding-agent sessions. For regular or automated use, please add your own API key. `aivo update` detects whether you installed via Homebrew or the install script and updates accordingly. Failed updates are rolled back automatically; a manual rollback is available if a new version misbehaves. ``` aivo update # force update even if installed via a package manager aivo update --force # restore the previous version from the last backup aivo update --rollback Copied! ``` Model limits come from [models.dev](https://models.dev) and ship baked into each release. `--sync-model-data` refreshes that snapshot between releases without touching the binary. ``` aivo update --sync-model-data Copied! ```