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" overhead of using multiple AI coding agents. Instead of managing agents in separate terminal tabs where context is lost between sessions, Multica provides a unified workspace where agents act as teammates, allowing humans to assign them tasks via issues and track their progress on a shared board.

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 "runtime" (a laptop or cloud server) to spawn and manage these CLIs. The system connects these runs to specific issues, maintaining a persistent execution log of tool calls and commands, and requires human review gates before any code is merged into the main branch.

Who it’s for

It is designed for software development teams and individual developers who use various AI coding agents and want to integrate them into a professional project management workflow with audit trails, cost tracking, and shared context.

Highlights

  • Agent Agnostic: Supports over 26 different agent CLIs, allowing users to switch providers via a dropdown.
  • Unified Workspace: Integrates agents into a board-based workflow where they pick up issues, report progress, and raise blockers.
  • Self-Hostable: Can be deployed via Docker Compose or Helm on private infrastructure with support for various Git hosts (GitHub, GitLab, Gitea, Forgejo).
  • Execution Transparency: Provides timestamped logs of every tool call and the ability to steer running agents in real-time.
  • Multi-Platform Access: Available via web, desktop (macOS, Windows, Linux), and mobile (iOS/iPadOS).

Related

  • Project
    Agenta-AI/agenta

    Agenta is an open‑source, self‑hostable workspace for building AI agents that can be chatted with, shared with a team, and run in the background. It supports many LLM providers, integrates with thousands of SaaS tools, offers permission controls, tracing, and scheduling, and provides a web UI plus a rich developer ecosystem.

  • Project
    NanmiCoder/cc-haha

    cc‑haha is a cross‑platform desktop workbench for Claude Code and other LLMs. It provides multi‑session chat, Git branch launching, diff review, built‑in browser preview, permission controls, model selection, image generation, visual sub‑agent and team management, dynamic workflow orchestration, request tracing, and macOS‑only “Computer Use” that lets agents control other apps without hijacking your mouse/keyboard. The app is built with Electron, React, TypeScript, and runs on the Bun runtime, supporting many model providers (Claude, ChatGPT, Grok, local Ollama, etc.) and integrates with IM platforms (Telegram, Slack, WeChat, etc.). Users download a binary for macOS/Windows/Linux, configure API keys, and can also run the underlying CLI for deeper customization.

  • Project
    Prorise-cool/Claude-Code-Multi-Agent

    Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.

  • Project
    johnson7788/MultiUserClaw

    MultiUserClaw is a Docker‑based SaaS framework that lets you run isolated AI assistants (Hermes agents) for many users. It includes a React front‑end, a FastAPI gateway for auth, container management and LLM proxying, per‑user Hermes containers, PostgreSQL storage, and features like knowledge bases, skill store, cron jobs, multi‑channel bots, and multi‑model support.

  • Project
    Team-Commonly/commonly

    An open-source coordination workspace where humans and AI agents collaborate using shared pods, persistent memory, and a GitHub-synced task board.