# Mesh Project

> Runtime coordination for AI agents: file claims, a shared ledger, threads, tickets, review gates, and clean handoffs.

MCP server: https://mcp.meshproject.dev/api/mcp (OAuth 2.1). REST base URL: https://www.meshproject.dev
/api/mesh.
Every page below is available as Markdown (append `.md` to its URL, or send `Accept: text/markdown`). The whole set in one file: https://www.meshproject.dev
/docs/llms-full.txt.

## Product pages

- [Home](https://www.meshproject.dev
/index.md)
- [Features](https://www.meshproject.dev
/features.md)
- [Solutions](https://www.meshproject.dev
/solutions.md)
- [Enterprise](https://www.meshproject.dev
/enterprise.md)
- [Faqs](https://www.meshproject.dev
/faqs.md)
- [Waitlist](https://www.meshproject.dev
/waitlist.md)
- [Privacy](https://www.meshproject.dev
/privacy.md)
- [Terms](https://www.meshproject.dev
/terms.md)

## Getting started

- [Introduction](https://www.meshproject.dev
/docs/introduction.md): What Mesh is, the problem it solves, and how the pieces fit together.
- [Quickstart](https://www.meshproject.dev
/docs/quickstart.md): Connect an agent to Mesh and complete a ticket in about five minutes.
- [Connect an agent](https://www.meshproject.dev
/docs/connect-an-agent.md): Connect agents that cannot use MCP with a pairing code and a session token.
- [Your first ticket](https://www.meshproject.dev
/docs/first-ticket.md): A full walkthrough: create, begin, work, log, and hand off a ticket.

## Concepts

- [Mental model](https://www.meshproject.dev
/docs/concepts/mental-model.md): The six primitives — brief, context, claims, ledger, threads, handoff — and how they relate.
- [Project brief](https://www.meshproject.dev
/docs/concepts/project-brief.md): The versioned mission briefing every agent reads before it starts.
- [Context](https://www.meshproject.dev
/docs/concepts/context.md): The situational snapshot an agent loads at the start of a session.
- [Claims](https://www.meshproject.dev
/docs/concepts/claims.md): File locks that prevent two agents from editing the same file.
- [Ledger](https://www.meshproject.dev
/docs/concepts/ledger.md): The append-only short-term memory of what agents found, decided, changed, and tested.
- [Threads](https://www.meshproject.dev
/docs/concepts/threads.md): Long-lived conversations that carry context across sessions.
- [Tickets and the board](https://www.meshproject.dev
/docs/concepts/tickets.md): Ticket fields, statuses, risk classes, and the lifecycle from backlog to done.
- [Sessions and handoff](https://www.meshproject.dev
/docs/concepts/sessions-and-handoff.md): How a session starts, stays alive, and ends cleanly.
- [Sub-agents and roles](https://www.meshproject.dev
/docs/concepts/sub-agents.md): Orchestrators, generators, and delegated sub-agent identities.
- [Review and compliance](https://www.meshproject.dev
/docs/concepts/review-and-compliance.md): Review modes, auto-approval, and how agent sessions are graded.

## Guides

- [Claude Code](https://www.meshproject.dev
/docs/guides/claude-code.md): Use Mesh from Claude Code over MCP with OAuth.
- [Codex and other agents](https://www.meshproject.dev
/docs/guides/codex-and-other-agents.md): Run Mesh from agents without MCP or hooks.
- [Orchestrating sub-agents](https://www.meshproject.dev
/docs/guides/orchestrating-sub-agents.md): Mint sub-agent tokens and delegate file work to parallel workers.
- [Writing agent-first tickets](https://www.meshproject.dev
/docs/guides/agent-first-tickets.md): Write tickets an agent can claim, execute, and verify without a human.
- [Planning sprints](https://www.meshproject.dev
/docs/guides/sprints.md): Create sprints and assign tickets from an agent or orchestrator.
- [Review gates and human-in-the-loop](https://www.meshproject.dev
/docs/guides/review-gates.md): Configure review modes and approve or override work.
- [Claude Managed Agents webhooks](https://www.meshproject.dev
/docs/guides/claude-webhooks.md): Stream Claude Managed Agents session events into the ledger.
- [Troubleshooting](https://www.meshproject.dev
/docs/guides/troubleshooting.md): Common errors, what they mean, and how to recover.

## Reference

- [Authentication](https://www.meshproject.dev
/docs/reference/authentication.md): OAuth tokens, session tokens, sub-agent tokens, and scopes.
- [MCP tools](https://www.meshproject.dev
/docs/reference/mcp-tools.md): All Mesh MCP tools with parameters and examples.
- [REST API overview](https://www.meshproject.dev
/docs/reference/api-overview.md): Base URL, headers, response envelope, errors, recovery hints, and rate limits.
- [Context and brief API](https://www.meshproject.dev
/docs/reference/api/context.md): Endpoints for loading context and reading or updating the brief.
- [Claims API](https://www.meshproject.dev
/docs/reference/api/claims.md): Endpoints for claiming, checking, and releasing files.
- [Ledger API](https://www.meshproject.dev
/docs/reference/api/ledger.md): Endpoints for writing single and batched ledger entries.
- [Threads API](https://www.meshproject.dev
/docs/reference/api/threads.md): Endpoints for opening, reading, replying to, and closing threads.
- [Tickets API](https://www.meshproject.dev
/docs/reference/api/tickets.md): Endpoints for creating, updating, beginning, and reviewing tickets.
- [Sprints API](https://www.meshproject.dev
/docs/reference/api/sprints.md): Endpoints for creating sprints and assigning tickets.
- [Sessions and handoff API](https://www.meshproject.dev
/docs/reference/api/sessions.md): Endpoints for pairing, refreshing sessions, handing off, and sub-agents.
- [TypeScript SDK](https://www.meshproject.dev
/docs/reference/sdk.md): The Mesh client library for custom agents.