🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
CLI for coding agents and model routing
Aivo is a Rust CLI that lets you launch several coding agents from one place and choose the model or provider for each run. It supports hosted APIs, gateways, and local GGUF models, and it includes Aivo Code, a built-in terminal agent with sessions, skills, and MCP servers.

Builders who want one terminal app for Claude Code, Codex, Gemini, Grok, and other coding agents.
You can switch agents and models without changing tools or rebuilding your workflow.
What it does
Run multiple agents from one CLI
Launch Claude Code, Codex, Gemini, OpenCode, Pi, Grok, and Aivo Code with the same command style.
Choose the model or provider
Use hosted APIs, AI gateways, or local GGUF files instead of being tied to one model source.
Store API keys locally
Manage keys with encrypted storage inside the app.
Track sessions and usage
Keep a unified view of sessions, logs, and token usage in the terminal.
Built-in Aivo Code agent
Use the included terminal agent with session tools, skills, MCP servers, and remote or local model support.
Plugin support
Extend Aivo through its plugin protocol documented in `docs/PLUGIN-PROTOCOL.md`.
How to get it
- 1macOS and Linux
curl -fsSL https://getaivo.dev/install.sh | bash
- 2Homebrew
brew install yuanchuan/tap/aivo
- 3Windows PowerShell
irm https://getaivo.dev/install.ps1 | iex
- 4The built-in aivo/starter provider works on first run, so you can try Aivo without an…
aivo "tell me a short story" aivo claude
- 5Add a provider to access more models
aivo keys add aivo claude --model moonshotai/kimi-k2.5
- 6Launch other supported agents the same way
aivo codex aivo gemini aivo opencode aivo pi aivo grok
README
Aivo /ˈeɪ.voʊ/ lets you use Claude Code, Codex, Gemini, OpenCode, Pi, Grok, and other coding agents with the model and provider you choose. It also includes Aivo Code, a built-in terminal coding agent.
Documentation · Install · Quick start · Aivo Code
Why Aivo?
- Run popular coding agents through one CLI.
- Use any model, from hosted APIs and AI gateways to local GGUF files.
- Manage API keys locally with encrypted storage.
- Work directly in the terminal with Aivo Code.
- Keep a unified view of sessions, logs, and token usage.
Install
macOS and Linux
curl -fsSL https://getaivo.dev/install.sh | bash
Homebrew
brew install yuanchuan/tap/aivo
Windows PowerShell
irm https://getaivo.dev/install.ps1 | iex
Quick start
The built-in aivo/starter provider works on first run, so you can try Aivo without an API key:
aivo "tell me a short story"
aivo claude
Add a provider to access more models:
aivo keys add
aivo claude --model moonshotai/kimi-k2.5
Launch other supported agents the same way:
aivo codex
aivo gemini
aivo opencode
aivo pi
aivo grok
Aivo Code
Aivo Code is the built-in terminal coding agent, with session tools, skills, MCP servers, and support for remote or local models.
aivo code
aivo code vercel::zai/glm-5.2
aivo code hf:lmstudio-community/Olmo-3-1025-7B-GGUF
aivo code -e "今天成都的天气"
Learn more
See getaivo.dev for commands, providers, models, configuration, plugins, and advanced usage.
License
Files in the repo
- .cargo
- .github
- docs
- src
- tests
- .gitignore
- build.rs
- Cargo.lock
- Cargo.toml
- CHANGELOG.md
- CLAUDE.md
- deny.toml
- LICENSE
- Makefile
- README.md
- rust-toolchain.toml
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More tools
The best-benchmarked open-source AI memory system. And it's free.
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
