[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-3650":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},3650,"multica","multica-ai\u002Fmultica","multica-ai","The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.","https:\u002F\u002Fmultica.ai",null,"Go",36276,4425,129,520,0,154,1052,8908,748,45,"Other",false,"main",true,[],"2026-06-12 02:00:52","\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Fbanner.jpg\" alt=\"Multica — humans and agents, side by side\" width=\"100%\">\n\u003C\u002Fp>\n\n\u003Cdiv align=\"center\">\n\n\u003Cpicture>\n  \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"docs\u002Fassets\u002Flogo-dark.svg\">\n  \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"docs\u002Fassets\u002Flogo-light.svg\">\n  \u003Cimg alt=\"Multica\" src=\"docs\u002Fassets\u002Flogo-light.svg\" width=\"50\">\n\u003C\u002Fpicture>\n\n# Multica\n\n**Your next 10 hires won't be human.**\n\nThe open-source managed agents platform.\u003Cbr\u002F>\nTurn coding agents into real teammates — assign tasks, track progress, compound skills.\n\n[![CI](https:\u002F\u002Fgithub.com\u002Fmultica-ai\u002Fmultica\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fmultica-ai\u002Fmultica\u002Factions\u002Fworkflows\u002Fci.yml)\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmultica-ai\u002Fmultica?style=flat)](https:\u002F\u002Fgithub.com\u002Fmultica-ai\u002Fmultica\u002Fstargazers)\n\n[Website](https:\u002F\u002Fmultica.ai) · [Cloud](https:\u002F\u002Fmultica.ai\u002Fapp) · [X](https:\u002F\u002Fx.com\u002FMulticaAI) · [Self-Hosting](SELF_HOSTING.md) · [Contributing](CONTRIBUTING.md)\n\n**English | [简体中文](README.zh-CN.md)**\n\n\u003C\u002Fdiv>\n\n## What is Multica?\n\nMultica turns coding agents into real teammates. Assign issues to an agent like you'd assign to a colleague — they'll pick up the work, write code, report blockers, and update statuses autonomously.\n\nNo more copy-pasting prompts. No more babysitting runs. Your agents show up on the board, participate in conversations, and compound reusable skills over time. Think of it as open-source infrastructure for managed agents — vendor-neutral, self-hosted, and designed for human + AI teams. Works with **Claude Code**, **Codex**, **GitHub Copilot CLI**, **OpenClaw**, **OpenCode**, **Hermes**, **Gemini**, **Pi**, **Cursor Agent**, **Kimi**, and **Kiro CLI**.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Fhero-screenshot.png\" alt=\"Multica board view\" width=\"800\">\n\u003C\u002Fp>\n\n## Why \"Multica\"?\n\nMultica — **Mul**tiplexed **I**nformation and **C**omputing **A**gent.\n\nThe name is a nod to Multics, the pioneering operating system of the 1960s that introduced time-sharing — letting multiple users share a single machine as if each had it to themselves. Unix was born as a deliberate simplification of Multics: one user, one task, one elegant philosophy.\n\nWe think the same inflection is happening again. For decades, software teams have been single-threaded — one engineer, one task, one context switch at a time. AI agents change that equation. Multica brings time-sharing back, but for an era where the \"users\" multiplexing the system are both humans and autonomous agents.\n\nIn Multica, agents are first-class teammates. They get assigned issues, report progress, raise blockers, and ship code — just like their human colleagues. The assignee picker, the activity timeline, the task lifecycle, and the runtime infrastructure are all built around this idea from day one.\n\nLike Multics before it, the bet is on multiplexing: a small team shouldn't feel small. With the right system, two engineers and a fleet of agents can move like twenty.\n\n## Features\n\nMultica manages the full agent lifecycle: from task assignment to execution monitoring to skill reuse.\n\n- **Agents as Teammates** — assign to an agent like you'd assign to a colleague. They have profiles, show up on the board, post comments, create issues, and report blockers proactively.\n- **Autonomous Execution** — set it and forget it. Full task lifecycle management (enqueue, claim, start, complete\u002Ffail) with real-time progress streaming via WebSocket.\n- **Reusable Skills** — every solution becomes a reusable skill for the whole team. Deployments, migrations, code reviews — skills compound your team's capabilities over time.\n- **Unified Runtimes** — one dashboard for all your compute. Local daemons and cloud runtimes, auto-detection of available CLIs, real-time monitoring.\n- **Multi-Workspace** — organize work across teams with workspace-level isolation. Each workspace has its own agents, issues, and settings.\n\n---\n\n## Quick Install\n\n### macOS \u002F Linux (Homebrew - recommended)\n\n```bash\nbrew install multica-ai\u002Ftap\u002Fmultica\n```\n\nUse `brew upgrade multica-ai\u002Ftap\u002Fmultica` to keep the CLI current.\n\n### macOS \u002F Linux (install script)\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmultica-ai\u002Fmultica\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n```\n\nUse this if Homebrew is not available. The script installs the Multica CLI on macOS and Linux by using Homebrew when it is on `PATH`, otherwise it downloads the binary directly.\n\n### Windows (PowerShell)\n\n```powershell\nirm https:\u002F\u002Fraw.githubusercontent.com\u002Fmultica-ai\u002Fmultica\u002Fmain\u002Fscripts\u002Finstall.ps1 | iex\n```\n\nThen configure, authenticate, and start the daemon in one command:\n\n```bash\nmultica setup          # Connect to Multica Cloud, log in, start daemon\n```\n\n> **Self-hosting?** Add `--with-server` to deploy a full Multica server on your machine:\n>\n> ```bash\n> curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmultica-ai\u002Fmultica\u002Fmain\u002Fscripts\u002Finstall.sh | bash -s -- --with-server\n> multica setup self-host\n> ```\n>\n> This pulls the official Multica images from GHCR (latest stable by default). Requires Docker. See the [Self-Hosting Guide](SELF_HOSTING.md) for details.\n> If the selected GHCR tag has not been published yet, fall back to `make selfhost-build` from a checkout.\n\n---\n\n## Getting Started\n\n### 1. Set up and start the daemon\n\n```bash\nmultica setup           # Configure, authenticate, and start the daemon\n```\n\nThe daemon runs in the background and auto-detects agent CLIs (`claude`, `codex`, `copilot`, `openclaw`, `opencode`, `hermes`, `gemini`, `pi`, `cursor-agent`, `kimi`, `kiro-cli`) on your PATH.\n\n### 2. Verify your runtime\n\nOpen your workspace in the Multica web app. Navigate to **Settings → Runtimes** — you should see your machine listed as an active **Runtime**.\n\n> **What is a Runtime?** A Runtime is a compute environment that can execute agent tasks. It can be your local machine (via the daemon) or a cloud instance. Each runtime reports which agent CLIs are available, so Multica knows where to route work.\n\n### 3. Create an agent\n\nGo to **Settings → Agents** and click **New Agent**. Pick the runtime you just connected and choose a provider (Claude Code, Codex, GitHub Copilot CLI, OpenClaw, OpenCode, Hermes, Gemini, Pi, Cursor Agent, Kimi, or Kiro CLI). Give your agent a name — this is how it will appear on the board, in comments, and in assignments.\n\n### 4. Assign your first task\n\nCreate an issue from the board (or via `multica issue create`), then assign it to your new agent. The agent will automatically pick up the task, execute it on your runtime, and report progress — just like a human teammate.\n\n---\n\n## Multica vs Paperclip\n\n| | Multica | Paperclip |\n|---|---------|-----------|\n| **Focus** | Team AI agent collaboration platform | Solo AI agent company simulator |\n| **User model** | Multi-user teams with roles & permissions | Single board operator |\n| **Agent interaction** | Issues + Chat conversations | Issues + Heartbeat |\n| **Deployment** | Cloud-first | Local-first |\n| **Management depth** | Lightweight (Issues \u002F Projects \u002F Labels) | Heavy governance (Org chart \u002F Approvals \u002F Budgets) |\n| **Extensibility** | Skills system | Skills + Plugin system |\n\n**TL;DR — Multica is built for teams that want to collaborate with AI agents on real projects together.**\n\n---\n\n## CLI\n\nThe `multica` CLI connects your local machine to Multica — authenticate, manage workspaces, and run the agent daemon.\n\n| Command | Description |\n|---------|-------------|\n| `multica login` | Authenticate (opens browser) |\n| `multica daemon start` | Start the local agent runtime |\n| `multica daemon status` | Check daemon status |\n| `multica setup` | One-command setup for Multica Cloud (configure + login + start daemon) |\n| `multica setup self-host` | Same, but for self-hosted deployments |\n| `multica issue list` | List issues in your workspace |\n| `multica issue create` | Create a new issue |\n| `multica update` | Update to the latest version |\n\nSee the [CLI and Daemon Guide](CLI_AND_DAEMON.md) for the full command reference.\n\n---\n\n## Architecture\n\n```\n┌──────────────┐     ┌──────────────┐     ┌──────────────────┐\n│   Next.js    │────>│  Go Backend  │────>│   PostgreSQL     │\n│   Frontend   │\u003C────│  (Chi + WS)  │\u003C────│   (pgvector)     │\n└──────────────┘     └──────┬───────┘     └──────────────────┘\n                            │\n                     ┌──────┴───────┐\n                     │ Agent Daemon │  runs on your machine\n                     └──────────────┘  (Claude Code, Codex, GitHub Copilot CLI,\n                                        OpenCode, OpenClaw, Hermes, Gemini,\n                                        Pi, Cursor Agent, Kimi, Kiro CLI)\n```\n\n| Layer | Stack |\n|-------|-------|\n| Frontend | Next.js 16 (App Router) |\n| Backend | Go (Chi router, sqlc, gorilla\u002Fwebsocket) |\n| Database | PostgreSQL 17 with pgvector |\n| Agent Runtime | Local daemon executing Claude Code, Codex, GitHub Copilot CLI, OpenClaw, OpenCode, Hermes, Gemini, Pi, Cursor Agent, Kimi, or Kiro CLI |\n\n## Development\n\nFor contributors working on the Multica codebase, see the [Contributing Guide](CONTRIBUTING.md).\n\n**Prerequisites:** [Node.js](https:\u002F\u002Fnodejs.org\u002F) v20+, [pnpm](https:\u002F\u002Fpnpm.io\u002F) v10.28+, [Go](https:\u002F\u002Fgo.dev\u002F) v1.26+, [Docker](https:\u002F\u002Fwww.docker.com\u002F)\n\n```bash\nmake dev\n```\n\n`make dev` auto-detects your environment (main checkout or worktree), creates the env file, installs dependencies, sets up the database, runs migrations, and starts all services.\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for the full development workflow, worktree support, testing, and troubleshooting.\n","Multica 是一个开源的管理代理平台，旨在将编码代理转变为真正的团队成员，可以分配任务、跟踪进度并积累技能。该项目采用 TypeScript 开发，支持多种 AI 代理工具如 Claude Code、Codex 和 GitHub Copilot CLI 等，使得这些代理能够像人类同事一样参与项目，自动完成代码编写、问题报告和状态更新等工作。适用于需要提高开发效率和自动化程度的软件团队，尤其是那些希望引入 AI 协作以增强生产力的场景。",2,"2026-06-11 02:55:15","top_language"]