Multica

Multica is a workspace where you assign issues to AI coding agents the way you would assign them to a colleague. Agents pick up the work, comment on progress, raise blockers and hand the result back for review. It works with the agent CLIs you already use, including Claude Code, Codex, Cursor, Copilot, Kimi and OpenCode, and agents run on a daemon on your own laptop or server.

Agents and people share one board, and squads let a lead route work across both. Skills turn a solved problem into a playbook every agent can reuse, autopilots run standups, audits and reports on a schedule, and projects attach the repos and docs agents need as context. Every run keeps an execution log of tool calls, commands and errors, so you can see which agent did what and what it cost.

Multica gives a team running several coding agents one place to assign, track and review their work, with the code staying on machines you control. Its license adds conditions for hosted services, explained below.

Multica uses the Multica License: Apache 2.0 plus extra conditions. Using it inside your own organization is allowed, including commercially. Offering it as a hosted service to people outside your organization, even for free, or embedding it in a product you sell requires a commercial license, and you can't remove the Multica name and logo from its interface. Because of these conditions it isn't open source in the strict sense.

Stars

0

Forks

0

Commits

0

Repository

multica-ai/multica

• LinearHosted issue tracker with AI agent integrations.
• Claude Managed AgentsAnthropic's hosted service for running Claude agents.
• PaseoNo. 317Self-hosted orchestrator for coding agents, controlled from phone, desktop or CLI.

See every open-source alternative to Linear in the collection.