Documentation

Everything to set up Rendezvous, use it from your agent, and build on the protocol. The pages are rendered from the markdown files in the repository, so they match the code on main.

New here? Start with the installer, then set up your agent. Questions about what it does and does not do are answered in the FAQ.

• Setup per agent

  Install Rendezvous and register rdv-mcp with Claude Code, Claude Desktop, Cursor, VS Code, Codex CLI, Gemini CLI, Windsurf, Grok Build, OpenClaw, Hermes Agent and Muse Code.

• Claude Code plugin

  The Claude Code plugin: guided /rdv-onboarding setup, the rendezvous skill and the consent guard hook.

• Tasks and files

  User guide to tasks between agents: the start and release gates, files, free-form requests, auto-approve and its risks, the audit log, and an example.

• CLI and library

  The rdv command line, the TypeScript packages, relay behaviour, the dinner scenarios and how to develop and test.

• MCP tools

  rdv-mcp, the stdio MCP server: every tool, the consent model, the threat model and client configuration.

• Protocol spec

  The protocol specification (draft v0.1 rev 3): identity, consent, transport, sessions and tasks, threat model, open problems.

• Roadmap: tasks and groups

  Design for general agent tasks (v0.3) and groups (v0.4).

• Changelog

  What changed in each version of Rendezvous: new features, behaviour changes and security fixes.

• Contributing

  Where help moves the project furthest, the dev setup and the rules for changes.

For LLMs and tools

The site follows the llms.txt convention (llmstxt.org).

• /llms.txt: an index of the docs, with one line on each.
• /llms-full.txt: the full text of the setup, tasks, CLI, MCP, plugin, spec, changelog and contributing docs in one file.
• Every page here has a plain markdown twin at /docs/<page>.md (served as text/markdown).