Welcome to Molecule AI
Multi-agent organisations as code — templates, plugins, channels, and the runtime that ties them together.
Molecule AI is an open platform for building, running, and operating
multi-agent organisations. You define your team in one YAML file
(org.yaml), pick the plugins each role needs, wire up the channels they
talk on, schedule their recurring work — and the platform takes care of the
rest.
Try it now
| Dashboard | app.moleculesai.app — create orgs, deploy agents |
| API | api.moleculesai.app — control plane REST API |
| Documentation | doc.moleculesai.app — you are here |
| Status | status.moleculesai.app — uptime monitoring |
| Self-host | Self-Hosting Guide — run on your own infrastructure |
What you can build
- Self-running engineering teams — PM, Dev Lead, frontend / backend / devops agents, security auditor, QA — all coordinating through A2A messages and scheduled audits, opening real PRs to your real repo.
- Research squads — market analysts, technical researchers, competitive intelligence agents that sweep the web on a cadence and write findings to shared memory.
- Product orgs — anything you can describe as a tree of roles and responsibilities.
- Hybrid teams — mix cloud-hosted agents with external agents running on your own infrastructure, edge devices, or other clouds.
How it works
- Templates. Describe your org as a YAML tree of workspaces. Each workspace is a real container running an LLM agent. Templates ship with sensible defaults so you can spin one up in one command.
- Plugins. Add capabilities to one role or all of them — guardrails, skills, slash commands, browser automation, MCP servers. Plugins compose; per-role overrides UNION with the defaults.
- Channels. Connect any role to Telegram, Slack, or Lark/Feishu so users can talk to agents directly from their existing tools.
- Schedules. Define recurring work in cron syntax. The runtime fires the prompt at the scheduled time, supervised against panics with a liveness watchdog.
- Tokens. Generate API tokens per workspace for secure authentication. Rotate, revoke, and audit from the dashboard or API.
- The canvas. A live visualisation of your org — every workspace as a node, every A2A message as an edge, every memory write tracked in real time.
Eight runtime adapters
| Runtime | Description |
|---|---|
| Claude Code | Anthropic Claude with code execution |
| LangGraph | LangChain ReAct agent with tools |
| OpenClaw | Multi-file prompt system with SOUL |
| CrewAI | Role-based agent with task delegation |
| AutoGen | Microsoft conversable agents |
| DeepAgents | Deep research with planning |
| Hermes | NousResearch Hermes-3 multi-provider |
| Gemini CLI | Google Gemini CLI workspace |
Integrate with everything
- MCP Server — 87 tools for managing Molecule AI from any MCP-compatible AI agent (Claude Code, Cursor, etc.)
- Python SDK —
pip install molecule-ai-sdk - External Agents — register any HTTP agent as a first-class workspace
Where to next
- New here? Read the Quickstart — spin up your first agent in under five minutes.
- Want the architecture tour? Start with Concepts and Architecture.
- Ready to build your own org? Jump to Org Templates.
- Want to connect your own agent? See External Agents.
- Need API access? Check Token Management and the API Reference.