Chatty DocumentationChatty
A desktop and terminal AI agent, built in Rust. Run multi-tool agents against the LLM provider you choose, with everything stored locally and an optional fully local setup through Ollama.
Why Chatty
Your provider, your data. Connect OpenRouter, Azure OpenAI or a local Ollama instance. Conversations, memory and settings stay in local files and a local SQLite database; nothing is hosted by Chatty.
An agent, not a chat box. The model can plan, call tools, read and edit files in a workspace you choose, run code in a sandbox, query spreadsheets and data files, search the web, and drive a real browser to check its own work. Every side-effecting action goes through an approval mode you control.
Two front ends, one engine. The desktop app and the terminal app share the same core, so the agent behaves the same whether you are chatting in a window or scripting chatty-tui headless in a pipeline. Sub-agents are just headless terminal instances.
Fast and native. Built on GPUI, the GPU-accelerated UI framework from the Zed editor. Markdown, code, LaTeX math, Mermaid diagrams, charts, PDFs and tables render natively in the transcript.
Download
| Platform | Format |
|---|---|
| macOS (Intel & Apple Silicon) | .dmg installer |
| Linux (x86_64) | .tar.gz archive or AppImage |
| Windows (x86_64) | .exe installer |
All builds are on GitHub Releases. The app checks for updates in the background and verifies them before installing.
Where to go next
| I want to… | Read |
|---|---|
| Install and start chatting | Getting started |
| Understand what the agent can do | Agents & tools · Security & approvals |
| Use the terminal app or sub-agents | Terminal interface · Sub-agents |
| Build a team of named workers | Tutorial: your first named worker · Tutorial: a small agentic team · Tutorial: an autonomous dev team |
| Write a plugin or an MCP integration | Build a WASM plugin · Extensions & MCP |
| Contribute to the code | Build and run · Contributing patterns |
| Look something up | Reference · Glossary |