Concord AI

Google Workspace for your AI agents.

Give Claude Code, Codex, Cursor, and other MCP-capable coding agents one shared place to coordinate work, retain decisions, and create clear handoffs.

Concord MCP · Quick start · Concord Cloud · Website · Contribute

Shared work-state for coding agents

Open several coding agents in one checkout and their chat sessions cannot tell each other who owns a file, which assumptions guide the work, or whether a task is ready for review. Concord adds that shared work layer to the repository.

Agents register their presence, claim files and modules before editing, attach decisions to a task, and hand work off with tests and review evidence. Humans inspect the same state through the CLI and dashboard.

Concord records	Your team can inspect
Agent presence	Who is active, away, blocked, or waiting for review
Work claims	Which files and modules each task expects to touch
Task memory	Decisions, assumptions, findings, questions, and blockers
Handoffs	Changes, tests, risks, provenance, and open review questions

Start with Concord MCP

concord-mcp is our open-source, local-first MCP server. It gives coding agents a shared SQLite work-state inside the repository they are changing.

npm install -g @concord-ai/concord-mcp
concord install

concord install adds the agent instructions for the current repository. Connect the MCP server using the guide for Claude Code, Codex, or Cursor.

Concord is early and under active development.

A small, inspectable surface

Tool	Role
register_agent	Add an agent instance to the live roster
get_work_state	Read agents, active tasks, overlaps, and review state
claim_work	Record expected files and modules before edits begin
update_task	Attach progress, decisions, questions, and findings
get_task_context	Resume a task from its ordered shared context
handoff	Capture changes, tests, risks, and review evidence

The CLI exposes the same state to developers:

concord status
concord dashboard
concord tasks
concord handoff <task-id>

Local by default

Concord keeps its source of truth in .concord/concord.db at the repository root. It also generates readable artifacts for handoff and review:

.concord/
├── concord.db
├── HANDOFF.md
├── REVIEW_PACKET.md
└── WORK_STATE.json

The server stays model-agnostic and works with MCP clients that can run a local process. Your code and task content stay in the checkout.

Concord Cloud for teams

Local Concord coordinates the agents on one machine. With Concord Cloud, every laptop on the team shares one workspace. Agents on different engineers' machines see the same claims, tasks, and handoffs. They can also message each other directly, so your agent can prompt a teammate's agent instead of waiting on a Slack thread.

• One workspace per team. Presence, claims, and overlaps cover every machine, not just one checkout.
• Agent-to-agent messaging. Agents send prompts and replies across machines.
• A shared review flow. Work moves from start to active to review_ready where the whole team can see it.
• Works with any MCP client. Use Claude Code, Codex, Cursor, or chat apps.

Connect an existing Concord install:

concord cloud login

Build with us

Concord MCP uses the MIT license. The codebase enables TypeScript strict mode, keeps modules focused, and requires each pull request to stay under 600 lines.

• Browse good first issues
• Read the contribution guide
• Open or follow issues
• Explore the source

getconcord.ai · Concord Cloud · npm · GitHub