AI
Zed's AI docs are organized around three areas:
| Area | Use it to choose | Examples |
|---|---|---|
| Agents | How agentic work runs in Zed | Zed Agent, External Agents, Terminal Threads |
| Model access | How Zed connects to language models | Zed-hosted models, API access, subscriptions, gateways, local models |
| Features | Which AI workflow you want to use | Agentic editing, inline edits, edit prediction, Git assistance |
Start with AI Quick Start if you know what you want to do. Use AI by Company if you know the company, subscription, model provider, agent, or CLI you want to use.
Agent Paths
Agent paths decide how agentic work runs in Zed.
- Zed Agent: Zed's native agent. It can use models configured through LLM Providers, including Zed-hosted models, provider API keys, supported subscriptions, gateways, and local models. It also uses built-in tools, profiles, skills, instructions, and MCP servers.
- External Agents: ACP-integrated agents that run through their own process and configuration.
- Terminal Threads: terminal-backed threads for running an agent CLI or TUI directly in Zed.
The Threads Sidebar is where you organize agent work. You can run multiple agent threads and Terminal Threads at once, each using a different agent and working against different projects.
See Agents for a comparison.
Model Access
Model access controls which models power the Zed Agent and other model-backed Zed AI features. Zed can use hosted models, provider API access, subscription sign-in, gateways, and local models.
See LLM Providers to choose a model access path.
AI Features
Zed has several AI-powered workflows:
- Agent Panel: prompt agents, add context, review changes, and manage active threads.
- Parallel Agents: run multiple threads across projects and worktrees.
- Inline Assistant: transform a selection in place.
- Edit Prediction: accept AI completions while you type.
- Git commit generation: generate commit messages from the Git panel.
Configure AI
Use AI Quick Start to choose the right setup path, configure model access, add agents or MCP servers, control tools, and turn AI off.
For privacy, provider data boundaries, and opt-in data sharing, see AI Privacy and Feedback and Training Data.