Multica
Multica is an open-source platform that treats AI coding agents as autonomous team members. You assign tasks to agents the same way you would to human colleagues; they pick the work up, execute it, stream progress, and manage their own lifecycle. The pitch is "project management for human + agent te
Canonical version: Multica.
Multica is an open-source platform that treats AI coding agents as autonomous team members. You assign tasks to agents the same way you would to human colleagues; they pick the work up, execute it, stream progress, and manage their own lifecycle. The pitch is "project management for human + agent teams"; coordination infrastructure around existing coding agents rather than yet another agent.
Why it exists
Most coding agents (Claude Code, Codex, Cursor, Copilot, Gemini, etc.) are powerful in isolation but invisible in team workflows. They don't appear in your task board, can't be assigned tickets, and produce no audit trail your team can browse. Multica adds the missing management layer: shared task queue, real-time activity feed, skill library, and a runtime dashboard that spans local daemons and cloud compute.
How it works
- Assignment: agents appear in the same assignee dropdowns as humans; you ticket them and they go to work
- Squads: agent leaders can delegate tasks to other agents in their team. Recursive routing
- Skill library: reusable capability packages any agent on the team can execute. Skill compounding across the org, not just per-user
- Runtime dashboard: one pane of glass over local daemons and cloud workers
- Activity feed: human and agent actions interleaved in real time; full visibility
Supported coding agents
Eleven integrations at last count: Claude Code, Codex, GitHub Copilot CLI, OpenCode, OpenClaw, Hermes, Gemini, Pi, Cursor Agent, Kimi, Kiro CLI. Agent-agnostic by design; you pick the model, Multica handles the orchestration.
Tech stack
- Frontend: Next.js 16 (App Router)
- Backend: Go (Chi router, sqlc, gorilla/websocket)
- Database: PostgreSQL 17 + pgvector
- Runtime: local daemon that shells out to the agent CLIs
Why it matters
Once you have more than one agent running in a team context, the bottleneck stops being "can the agent code" and becomes "who knows what's happening". Multica is betting that the next layer of leverage is coordination, not capability; task routing, skill reuse, and shared visibility. That makes it a complement to AI Agent Orchestration thinking and a practical example of a Multi-Agent System (MAS) in software engineering. Self-hostable and open source, which is the right shape for something that wants to sit inside an org's development workflow.
References
- Website: https://multica.ai/
- Repo: https://github.com/multica-ai/multica
Related
- Claude Code
- AI Agents
- AI Agent Orchestration
- Multi-Agent System (MAS)
- Claude Code Agent Teams
- Cursor Cloud Agents
- Open Source
About Sébastien
I'm Sébastien Dubois, and I'm on a mission to help knowledge workers escape information overload. After 20+ years in IT and seeing too many brilliant minds drowning in digital chaos, I've decided to help people build systems that actually work. Through the Knowii Community, my courses, products & services and my Website/Newsletter, I share practical and battle-tested systems.
I write about Knowledge Work, Personal Knowledge Management, Note-taking, Lifelong Learning, Personal Organization, Productivity, and more. I also craft lovely digital products and tools.
If you want to follow my work, then become a member and join our community.
Ready to get to the next level?
If you're tired of information overwhelm and ready to build a reliable knowledge system:
- 📚 KM for Beginners — 10+ hours of structured video lessons
- 🚀 Obsidian Starter Kit — Ready-made vault with 40+ templates
- 💼 Knowledge Worker Kit — Complete guides + lifetime community
- 🦉 1-on-1 Coaching — Personalized guidance
- 🎯 Join Knowii — Community + ALL courses & tools
Found this valuable? Share it with someone who needs it.