# PaneVibe

> An IDE for coding agents with real terminal sessions, an editor, worktrees, and a built in browser.

## Primary
- [Documentation](https://panevibe.com/docs/): Human-readable documentation
- [Documentation index](https://panevibe.com/docs/index.md): Markdown documentation index
- [Full context](https://panevibe.com/llms-full.txt): Complete documentation in one text file
- [Source](https://github.com/brandonmlicea/panevibe): MIT-licensed source repository

## Documentation
- [Getting started](https://panevibe.com/docs/getting-started.md): Clone PaneVibe, run one setup command, and open your first real agent CLI in a PTY.
- [Terminal-first architecture](https://panevibe.com/docs/terminal-first.md): The PTY is the source of truth. Chat is a readable projection with the raw terminal always available.
- [Agents and models](https://panevibe.com/docs/agents-and-models.md): Use native agent CLIs when they exist, or connect any OpenAI-compatible endpoint for direct model access.
- [Browser and MCP](https://panevibe.com/docs/browser-and-mcp.md): Six built-in MCP servers and two deliberately different browser surfaces ship inside the binary.
- [Security and privacy](https://panevibe.com/docs/security-and-privacy.md): Localhost transport, no telemetry, OS-encrypted credentials, and explicit workspace permissions.
- [Configuration](https://panevibe.com/docs/configuration.md): Everything has a working default; environment variables are escape hatches rather than a required setup surface.
- [Contributing](https://panevibe.com/docs/contributing.md): Keep changes inside one concern, preserve the PTY execution model, and run the focused release gates.