#66th of 48 in Agent platforms
Multica
Issue board where coding agent CLIs are assigned work like teammates
- Stars
- 53.7k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Go
339 on 26 Mar 202653,688 on 22 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Multica is a workspace with an issue board where you assign tasks to coding agents such as Claude Code, Codex, Cursor and Kimi. A daemon on your own machine spawns the installed agent CLIs, keeps a timestamped execution log, and moves finished work to review. The backend is Go with PostgreSQL 17, with web, Electron desktop and Expo mobile clients.
Who it is for: Teams running several coding agents who want a shared, reviewable task board
Ranked among open-source alternatives to Copilot Studio (#6 of 10).
Strengths
- Drives 26 existing agent CLIs, so switching providers is a dropdown change
- Code runs on your own daemon machine, not on the Multica server
- Per-run execution log, cost analytics, review gates, retries and timeouts
- Self-host via Docker Compose or Helm; GitHub, GitLab, Gitea and Forgejo supported
Weaknesses
- Ships no model; needs at least one agent CLI installed and signed in
- Custom Multica License: Apache 2.0 plus conditions on hosting, embedding, branding
- Self-hosting needs Docker and PostgreSQL 17 alongside the Go backend
- iOS app builds from source only; some chat channels are community-maintained
What it needs
- no GPU
- Docker + Compose
- Needs Docker, PostgreSQL 17, Agent CLI (Claude Code, Codex, Cursor, etc.)
- Models: Claude Code, OpenAI Codex, Cursor Agent, GitHub Copilot CLI, OpenCode
Quick answers
Is Multica open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Can you run Multica with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does Multica need a GPU?
No, it runs without one.
Also in Agent platforms
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 94 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 94 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 93 out of 100 |
| #4 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |
| #5 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 88 out of 100 |