gptme documentation#
Welcome to the documentation for gptme!
gptme is a personal AI assistant and agent platform that runs in your terminal and browser, equipped with powerful tools to execute code, edit files, browse the web, and more - acting as an intelligent copilot for your computer. The core components include:
gptme CLI: The main command-line interface for terminal-based interactions
gptme-server: A server component for running gptme as a service
gptme-webui: A web interface for browser-based interactions
gptme-agent-template: A template for creating custom AI agents
The system can execute python and bash, edit local files, search and browse the web, and much more through its rich set of built-in tools and extensible tool system. You can see what’s possible in the Examples and Demos, from creating web apps and games to analyzing data and automating workflows.
See the README file for more general information about the project.
Where to start#
New to gptme? Install it with Getting Started, learn the basics in Usage, and try the Examples.
Choose a model: pick a model, set up its provider, and tune gptme with its configuration.
Pick an interface: the CLI, the TUI, the desktop and Android app, gptme.ai in the cloud, your editor, or channels like GitHub, email, chat, and voice.
Run it yourself: the Server serves the web UI and the REST API.
Give it context: teach it with Lessons and Skills, and let it remember across sessions with Memory.
Build on it: run persistent Agents, or extend gptme with Plugin System, custom tools, Hooks, and MCP.
Contribute: see Contributing.