Vibe Coding Discovermultica
View on GitHubMake humans and AI agents work as one team — open-source and self-hostable.
Multica is a self-hostable workspace where you assign issues to AI coding agents as teammates: agents pick up work on your own runtime daemon, comment progress, and hand back a diff for review. It drives 26 agent CLIs (Claude Code, Codex, Cursor, Kimi...) with execution logs, token cost tracking, squads, and autopilots
Use Cases
Assign GitHub-style issues to AI coding agents as teammatesRun agent standups, audits, and reports on a cron scheduleSelf-host an agent workspace on your own infrastructureReview agent-produced diffs and PRs before mergingTrack per-run token usage and cost per agent/issueRoute work across squads of agents and humansReplay timestamped agent tool calls and execution logsTrigger agent work from Slack, Telegram, Lark, DingTalk, WeComDrive the workspace from CLI/API or via Claude Code, Codex, CursorGive agents reusable playbooks via skillsConnect agents to self-hosted Git hosts (GitLab, Gitea, Forgejo)Enforce permission scopes on which agents a member can run
Built With
- Language
- Go
- Frameworks
- Go · Next.js · React · TypeScript · PostgreSQL · Electron · Docker Compose · Helm · Turborepo · pnpm · Playwright
Tags
ai-agents · agent-orchestration · multi-agent · coding-agents · issue-tracking · self-hosted · kanban-board · agent-cli · workflow-automation · daemon · autopilots · execution-logs · team-collaboration · claude-code · codex · skills