Works with Claude Code Codex Gemini CLI OpenCode Amp Pi Oh My Pi GitHub Copilot Grok CLI
$ Install aivo with script or package managers.
curl -fsSL https://getaivo.dev/install.sh | bash irm https://getaivo.dev/install.ps1 | iex brew install yuanchuan/tap/aivo Run a coding agent.
aivo claude
# or codex, gemini, opencode, pi, amp, grok Add API keys from any provider you trust. Keys are encrypted and stored locally, so you can manage them and switch anytime.
# 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 Move keys between machines through a single password-encrypted file.
# prompts for a password
aivo keys export ~/keys.aivo
# same password on the other machine, or pass a URL
aivo keys import ~/keys.aivo
aivo keys import https://example.com/keys.aivo
# non-interactive (CI / scripts)
aivo keys export ~/keys.aivo --password-stdin <<< "my secret"
# 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
Launch a coding agent with any provider or model you want. All extra arguments are passed through to the underlying tool.
aivo claude 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
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
Per-slot models Claude Code runs multiple models in a single session, haiku/sonnet/opus slots plus reasoning 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 claude --sonnet-model deepseek-v4-pro --haiku-model deepseek-v4-flash
aivo claude --reasoning-model gpt-5.4 --subagent-model claude-haiku-4-5
# open the picker for one slot
aivo claude --opus-model
aivo codex Use a saved API key with -k, or omit the value to open the picker.
aivo codex -k vercel
aivo codex -k
Pin a model with -m, or omit the value to open the model picker.
aivo codex -m xiaomi/mimo-v2-pro
aivo codex -m
Codex desktop app (macOS only) 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 aivo gemini Use a saved API key with -k, or omit the value to open the picker.
aivo gemini -k google
aivo gemini -k
Pin a model with -m, or omit the value to open the model picker.
aivo gemini -m gemini-2.5-pro
aivo gemini -m
aivo opencode Use a saved API key with -k, or omit the value to open the picker.
aivo opencode -k openrouter
aivo opencode -k
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
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 Use a saved API key with -k, or omit the value to open the picker.
aivo amp -k openrouter
aivo amp -k
Pin a model with -m, or omit the value to open the model picker.
aivo amp -m gpt-5.4
aivo amp -m
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
aivo pi Use a saved API key with -k, or omit the value to open the picker.
aivo pi -k cursor
aivo pi -k
Pin a model with -m, or omit the value to open the model picker.
aivo pi -m composer-2.5
aivo pi -m
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
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 Use a saved API key with -k, or omit the value to open the picker.
aivo omp -k openrouter
aivo omp -k
Pin a model with -m, or omit the value to open the model picker.
aivo omp -m deepseek-v4-pro
aivo omp -m
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 Use a saved API key with -k, or omit the value to open the picker.
aivo copilot -k openrouter
aivo copilot -k
Pin a model with -m, or omit the value to open the model picker.
aivo copilot -m claude-sonnet-4.6
aivo copilot -m
Install the plugin first Grok CLI support ships as a separate plugin. Install it once, then run it like any other agent.
aivo plugins install github:yuanchuan/aivo-grok
aivo grok Use a saved API key with -k, or omit the value to open the picker.
aivo grok -k openrouter
aivo grok -k
Pin a model with -m, or omit the value to open the model picker.
aivo grok -m gpt-5.4
aivo grok -m
Without a tool name, aivo run opens an interactive picker of agents and plugins, with your last choice selected by default.
aivo run
Pin a coding agent and its usual flags under one name, then launch the whole thing with aivo <name> (or the long form, aivo run <name>). 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
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./agents.--share or /share.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
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
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
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
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.
# 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
--json prints the raw upstream model list for scripts. The shape depends on the provider, pipe to jq to explore and filter.
aivo models --json
aivo models -k openrouter --json | jq
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
Run any open-weight GGUF directly from a Hugging Face repo. The first time you reference a model, aivo downloads the file to ~/.config/aivo/cache/huggingface and serves it through a bundled llama-server. Subsequent runs reuse the cached file.
The hf: prefix and full https://huggingface.co/… URLs are accepted anywhere a model name works, in aivo code, a coding agent's -m, the bare aivo shortcut, etc.
aivo hf:Qwen/Qwen2.5-0.5B-Instruct-GGUF
aivo https://huggingface.co/allenai/Olmo-3-1025-7B
GGUF repos usually publish several quantizations. Append :<quant> (e.g. Q5_K_M, Q4_K_M) to pick a specific file; if you don't, aivo prompts you to choose the first time it downloads.
aivo code 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
Pass hf: wherever -m/--model is accepted. Combine with the 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
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:
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 <repo> --quant Q5_K_M
aivo hf rm <repo> --all -y
# wipe the whole cache
aivo hf clean -y
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.
aivo serve
aivo serve --port 8080
aivo serve --host 0.0.0.0
If a request hits a rate limit (429) or server error (5xx), aivo retries with the next saved key automatically.
aivo serve --failover
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
aivo serve --auth-token
aivo serve --auth-token my-secret
aivo serve --cors
aivo serve --timeout 60
curl http://localhost:24860/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "hello"}]}' 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.
# recent activity in the current project
aivo logs
# every project on this machine
aivo logs --all
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
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
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
# 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
$ 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 ██▋ 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 · Poolside Poolside's second-generation coding agent model in the S size class. Once aivo is installed, you can use it straight away.
aivo "tell me a short story"
aivo code Link your device to an account for higher daily limits on the starter pool.
aivo account login
aivo account usage 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
Model limits come from 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