multica-ai/multica

Make humans and AI agents work as one team — open-source and self-hostable.

What it solves

Multica addresses the fragmentation and "babysitting" required when using multiple AI coding agents. Instead of managing separate terminal tabs and repeatedly providing context to different tools, it provides a unified workspace where agents are treated as teammates who can be assigned issues, track progress, and collaborate with humans in a single environment.

How it works

Multica acts as an orchestration layer that drives existing agent CLIs (such as Claude Code, Codex, and Cursor) rather than providing its own model. It uses a local daemon installed on a user's machine (the "runtime") to execute these CLIs. Users assign tasks via a board-style interface; the agent picks up the issue, executes commands on the controlled runtime, logs its tool calls and costs, and submits the work for human review before it is merged.

Who it’s for

It is designed for software development teams and individual developers who use multiple AI coding agents and want a structured, auditable way to manage their work and maintain context across different AI tools.

Highlights

  • Broad Compatibility: Supports 23 different agent CLIs, including Claude Code, Cursor, and GitHub Copilot.
  • Agent-as-Teammate: Agents are assigned to issues, report blockers, and move work across a board just like human developers.
  • Full Auditability: Provides execution logs for every tool call and command, along with per-run token usage and cost tracking.
  • Flexible Deployment: Can be self-hosted via Docker Compose or Helm and integrates with various Git hosts (GitHub, GitLab, Gitea, Forgejo).
  • Multi-platform Access: Available via web, desktop (macOS, Windows, Linux), and mobile (iOS).

Related

  • Project
    stablyai/orca

    An AI orchestrator that lets developers run multiple CLI-based coding agents in parallel isolated worktrees to compare results and accelerate development.

  • Project
    xintaofei/codeg

    A multi-agent coding workspace that aggregates various AI coding agents into a single interface, enabling collaboration and collaboration and task management via git worktrees.

  • Project
    openteams-lab/openteams

    A local-first AI desktop app that provides a unified workspace for coordinating multiple AI coding agents, allowing them to share context and work within developer-controlled workflows.

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents from different runtimes can share context, files, and a browser.

  • Project
    YoanWai/agent-manager

    A terminal-based manager for AI coding agents that allows you to run multiple CLI agents side-by-side with integrated diff review and live status tracking.