Multica

Multica is an open-source managed agents platform that transforms coding agents into first-class teammates on your engineering team. Assign issues to an agent just like you'd assign to a colleague — they pick up the work, write code, report blockers, and update statuses autonomously. It supports a wide range of agent CLIs including Claude Code, Codex, GitHub Copilot CLI, OpenClaw, OpenCode, Hermes, Gemini, Pi, Cursor Agent, Kimi, and Kiro CLI, and is designed for vendor-neutral, self-hosted or cloud deployments.

• Agents as Teammates — agents have profiles, show up on the board, post comments, create issues, and report blockers proactively, just like human colleagues.
• Autonomous Execution — full task lifecycle management (enqueue, claim, start, complete/fail) with real-time progress streaming via WebSocket; set it and forget it.
• Reusable Skills — every solution becomes a reusable skill for the whole team; deployments, migrations, and code reviews compound your team's capabilities over time.
• Unified Runtimes — one dashboard for all your compute, supporting local daemons and cloud runtimes with auto-detection of available agent CLIs and real-time monitoring.
• Multi-Workspace — organize work across teams with workspace-level isolation; each workspace has its own agents, issues, and settings.
• CLI Tooling — install via Homebrew, install script, or PowerShell; use multica setup to configure, authenticate, and start the daemon in one command.
• Self-Hosting Support — deploy a full Multica server on your own machine using Docker and the official GHCR images with multica setup self-host.
• Modern Architecture — Next.js 16 frontend, Go backend (Chi + WebSocket), PostgreSQL 17 with pgvector, and a local agent daemon for flexible, scalable deployments.