docs/src/ai/overview.md
Zed is an open-source AI code editor. AI runs throughout the editing experience: agents that read and write your code, inline transformations, code completions on every keystroke, and conversations with models in any buffer.
Zed's AI features run inside a native, GPU-accelerated application built in Rust. There is no Electron layer between you and the model output.
The Agent Panel is where you work with AI agents. Agents can read files, edit code, run terminal commands, search the web, and access diagnostics through built-in tools.
You can extend agents with additional tools through MCP servers, control what they can access with tool permissions, and shape their behavior with rules.
The Inline Assistant works differently: select code or a terminal command, describe what you want, and the model rewrites the selection in place. It works with multiple cursors.
Edit Prediction provides AI code completions on every keystroke. Each keypress sends a request to the prediction provider, which returns single or multi-line suggestions you accept with tab.
The default provider is Zeta, Zed's open-source model trained on open data. You can also use GitHub Copilot, or Codestral.
Text Threads are conversations with models inside any buffer. They work like a regular editor with your keybindings, multiple cursors, and standard editing features. Content is organized into message blocks with roles (You, Assistant, System).
New to Zed? Start with Getting Started, then come back here to set up AI. For a higher-level overview, see zed.dev/ai.