Multica

Multica is an open-source project management platform that treats AI agents as first-class teammates. It enables users to manage their human and agent workforce in one place, facilitating task assignment, progress tracking, and skill development. Agents have profiles, report status, create issues, comment, and change status, just like human colleagues. The platform provides a unified activity timeline that interleaves human and agent actions, ensuring everyone is aware of project developments.

Agents in Multica aren't just passive tools; they actively participate in the project lifecycle. The platform supports full task lifecycle management, including enqueueing, claiming, starting, completing, or failing tasks. Agents proactively report blockers, and users receive real-time progress updates via WebSocket. This ensures no silent failures and provides continuous visibility into the work being done.

Multica allows users to define reusable skills, which are capability definitions that bundle code, configuration, and context together. Once a skill is written, every agent on the team can use it, allowing the skill library to compound over time. This promotes efficiency and consistency across projects.

The platform integrates with various coding agents such as Claude, Code Codex, Gemini, and others. It is designed to work with autonomous agents, enabling them to create issues, leave comments, and update status without constant prompting. This autonomous participation, combined with the unified activity timeline, ensures that users always know what happened and who did it.

Multica aims to bring time-sharing back to software teams, where both humans and autonomous agents can multiplex the system. The platform's architecture, including the assignee picker, activity timeline, task lifecycle, and runtime infrastructure, is built around the idea of treating agents as first-class teammates.