[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74631":3},{"id":4,"name":5,"fullName":6,"owner":5,"repo":5,"description":7,"homepage":8,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":9,"rankLanguage":9,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":36,"readmeContent":37,"aiSummary":38,"trendingCount":15,"starSnapshotCount":15,"syncStatus":39,"lastSyncTime":40,"discoverSource":41},74631,"AgentsMesh","AgentsMesh\u002FAgentsMesh","The AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.","https:\u002F\u002Fagentsmesh.ai",null,"Go",2202,220,123,7,0,15,36,168,45,107.03,"Other",false,"main",[25,26,27,28,29,30,31,32,33,34,35],"agent-orchestration","agentsmesh","ai-agent","ai-agent-workforce-platform","ai-coding","aider","claude-code","codex-cli","gemini-cli","multi-agent","self-hosted","2026-06-12 04:01:15","\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fimages\u002Flogo.svg\" alt=\"AgentsMesh\" height=\"60\" \u002F>\n\u003C\u002Fp>\n\n\u003Ch3 align=\"center\">Where teams scale beyond headcount.\u003C\u002Fh3>\n\n\u003Cp align=\"center\">\n  The AI Agent Workforce Platform.\u003Cbr\u002F>\n  Give every team member an AI agent squad — assign tasks, track progress, and let them collaborate autonomously.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fagentsmesh.ai\">Website\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fagentsmesh.ai\u002Fdocs\">Docs\u003C\u002Fa> ·\n  \u003Ca href=\"#quick-start\">Quick Start\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002F3RcX7VBbH9\">Discord\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fx.com\u002Fagentsmeshai\">X\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fagentsmesh\">LinkedIn\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAgentsMesh\u002FAgentsMesh\u002Factions\u002Fworkflows\u002Fci.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FAgentsMesh\u002FAgentsMesh\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg?branch=main\" alt=\"CI\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAgentsMesh\u002FAgentsMesh\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-BSL--1.1-blue\" alt=\"License\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fhub.docker.com\u002Fu\u002Fagentsmesh\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocker-hub-blue?logo=docker\" alt=\"Docker Hub\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FVaXImaly3dM\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FVaXImaly3dM\u002Fmaxresdefault.jpg\" alt=\"AgentsMesh Demo Video\" width=\"720\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\n## What is AgentsMesh?\n\nAgentsMesh is **The AI Agent Workforce Platform** — where teams scale beyond headcount. Instead of running agents one-at-a-time on your local machine, AgentsMesh lets you spin up **remote AI workstations (AgentPods)**, coordinate **multi-agent collaboration** through channels and pod bindings, and track everything via integrated **task management** — all from a single web console.\n\nIndividual productivity has peaked. The next frontier is organizational. AgentsMesh turns AI agents from solo tools into a coordinated workforce.\n\n**BYOK (Bring Your Own Key)** — You provide your own AI API keys. No usage caps. Full cost control.\n\n## Features\n\n- **AgentPod** — Remote AI workstations with web terminal, Git worktree isolation, and real-time streaming. Run multiple concurrent pods.\n- **Multi-Agent Collaboration** — Coordinate agents through channels and pod bindings. Visualize the collaboration topology in real-time.\n- **Task Management** — Kanban board with ticket-pod binding, progress tracking, and MR\u002FPR integration.\n- **Self-Hosted Runners** — Deploy runners on your own infrastructure. Your code never leaves your environment.\n- **Multi-Agent Support** — Claude Code, Codex CLI, Gemini CLI, Aider, OpenCode, and any custom terminal-based agent.\n- **Multi-Git Provider** — GitLab, GitHub, and Gitee integration.\n- **Multi-Tenant** — Organization > Team > User hierarchy with row-level isolation.\n- **Enterprise Ready** — SSO, RBAC, audit logs, air-gapped deployment support.\n\n## Getting Started\n\nThe fastest way to use AgentsMesh is through our hosted service at **[agentsmesh.ai](https:\u002F\u002Fagentsmesh.ai)** — sign up, connect your Git provider, and start running agents in minutes.\n\n### 1. Install the Runner\n\nThe Runner is a lightweight daemon that runs on your machine and executes AI agents locally. Your code stays on your infrastructure.\n\n```bash\ncurl -fsSL https:\u002F\u002Fagentsmesh.ai\u002Finstall.sh | sh\n```\n\n> See the [Runner README](runner\u002F) for more installation options (deb, rpm, Windows, etc.)\n\n### 2. Login\n\n```bash\nagentsmesh-runner login\n```\n\nThis opens your browser to authenticate. For headless environments (SSH, remote server):\n\n```bash\nagentsmesh-runner login --headless\n```\n\nFor self-hosted deployments, add `--server`:\n\n```bash\nagentsmesh-runner login --server https:\u002F\u002Fyour-server.com\n```\n\n### 3. Run\n\n```bash\nagentsmesh-runner run\n```\n\nOr install as a system service for always-on operation:\n\n```bash\nagentsmesh-runner service install\nagentsmesh-runner service start\n```\n\nOnce the runner is online, create an **AgentPod** from the web console and start coding with your AI agents.\n\n## Architecture\n\nAgentsMesh separates **control plane** from **data plane** — orchestration commands travel through gRPC with mTLS, while terminal I\u002FO streams through a Relay cluster.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fimages\u002Farchitecture.svg\" alt=\"AgentsMesh Architecture\" width=\"680\" \u002F>\n\u003C\u002Fp>\n\n| Component | Description |\n|-----------|-------------|\n| **Backend** | Go API server — auth, org\u002Fteam management, pod lifecycle, task management |\n| **Web** | Next.js frontend — dashboard, web terminal, kanban, topology visualization |\n| **Relay** | Terminal relay cluster — low-latency WebSocket pub\u002Fsub between runners and browsers |\n| **Runner** | Self-hosted Go daemon — connects to Backend (gRPC+mTLS) and Relay (WebSocket), runs AI agents in isolated PTY sandboxes |\n| **Web-Admin** | Internal admin console — user\u002Forg\u002Frunner management, audit logs |\n\n## Quick Start\n\n### One-Command Setup (Docker)\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FAgentsMesh\u002FAgentsMesh.git\ncd AgentsMesh\u002Fdeploy\u002Fdev\n.\u002Fdev.sh\n```\n\nThis starts the full stack: PostgreSQL, Redis, MinIO, Backend, Relay, Traefik, and a local Next.js frontend with hot reload.\n\n**Access:**\n\n| Service | URL |\n|---------|-----|\n| Web Console | http:\u002F\u002Flocalhost:3000 |\n| API | http:\u002F\u002Flocalhost:80\u002Fapi |\n\n**Test Accounts:**\n\n| Role | Email | Password |\n|------|-------|----------|\n| User | dev@agentsmesh.local | devpass123 |\n| Admin | admin@agentsmesh.local | adminpass123 |\n\n> Ports are dynamically allocated per worktree. Check `deploy\u002Fdev\u002F.env` for actual values.\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Manual Setup\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n**Prerequisites:** Go 1.24+, Node.js 20+, pnpm, Docker\n\n```bash\n# 1. Start infrastructure\ncd deploy\u002Fdev && .\u002Fdev.sh\n\n# 2. Backend (auto-starts in Docker with hot reload)\ndocker compose logs -f backend\n\n# 3. Frontend (local with Turbopack)\ncd clients\u002Fweb && pnpm install && pnpm dev\n```\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Production Deployment\u003C\u002Fstrong>\u003C\u002Fsummary>\n\nDocker images are published to Docker Hub on every push to `main`:\n\n```\nagentsmesh\u002Fbackend:sha-xxxxxxx\nagentsmesh\u002Fweb:sha-xxxxxxx\nagentsmesh\u002Fweb-admin:sha-xxxxxxx\nagentsmesh\u002Frelay:sha-xxxxxxx\n```\n\nTagged releases (`v*`) get semver tags:\n\n```\nagentsmesh\u002Fbackend:1.0.0\nagentsmesh\u002Fbackend:1.0\n```\n\nSee [deploy\u002Fselfhost\u002F](deploy\u002Fselfhost\u002F) for self-hosted deployment guide.\n\n\u003C\u002Fdetails>\n\n## Supported Agents\n\n| Agent | Provider | Description |\n|-------|----------|-------------|\n| [Claude Code](https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fagents-and-tools\u002Fclaude-code\u002Foverview) | Anthropic | Autonomous AI coding agent |\n| [Codex CLI](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex) | OpenAI | OpenAI's code generation CLI |\n| [Gemini CLI](https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-cli) | Google | Google Gemini CLI |\n| [Aider](https:\u002F\u002Fgithub.com\u002FAider-AI\u002Faider) | Open Source | AI pair programming in the terminal |\n| [OpenCode](https:\u002F\u002Fgithub.com\u002Fopencode-ai\u002Fopencode) | Open Source | Open source AI coding tool |\n| Custom | Any | Any terminal-based agent |\n\n## Tech Stack\n\n| Layer | Technology |\n|-------|-----------|\n| Backend | Go (Gin + GORM) |\n| Frontend | Next.js (App Router) + TypeScript + Tailwind CSS |\n| Database | PostgreSQL + Redis |\n| Storage | MinIO (S3-compatible) |\n| API | REST + gRPC (bidirectional streaming) |\n| Security | mTLS for runner connections, JWT for web auth |\n| Real-time | gRPC streaming (Runner ↔ Backend), WebSocket (Relay ↔ Browser) |\n| Reverse Proxy | Traefik |\n\n## Project Structure\n\n```\nAgentsMesh\u002F\n├── backend\u002F          # Go API server\n├── clients\u002F          # Frontend clients (web, web-admin, desktop)\n│   ├── web\u002F          # Next.js frontend\n│   ├── web-admin\u002F    # Admin console (Next.js)\n│   └── desktop\u002F      # Electron desktop app\n├── runner\u002F           # Self-hosted runner daemon (Go)\n├── relay\u002F            # Terminal relay server (Go)\n├── proto\u002F            # Protocol Buffers definitions\n├── ci\u002F               # CI Dockerfiles\n├── deploy\u002F\n│   ├── dev\u002F          # Docker Compose dev environment\n│   └── selfhost\u002F     # Self-hosted deployment guide\n└── docs\u002F             # Architecture docs and RFCs\n```\n\n## Contributing\n\nWe welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n- [Code of Conduct](CODE_OF_CONDUCT.md)\n- [Security Policy](SECURITY.md)\n\n## License\n\n[Business Source License 1.1](LICENSE) (BSL-1.1)\n\n- **Change Date:** 2030-02-28\n- **Change License:** GPL-2.0-or-later\n\nThe BSL allows you to use, copy, and modify the software for non-production purposes. Production use requires a commercial license until the change date, after which the software becomes available under GPL-2.0-or-later. See [LICENSE](LICENSE) for the full terms and additional use grant.\n","AgentsMesh是一个AI代理工作平台，旨在通过为团队成员配备AI代理小队来扩展团队能力。其核心功能包括远程AI工作站（AgentPods）、多代理协作、任务管理和自托管运行器等，支持Claude Code、Codex CLI等多种AI代理工具，并集成了GitLab、GitHub等代码仓库服务。AgentsMesh适合需要提高团队生产力和协作效率的企业或开发者使用，尤其是在处理复杂项目时能够显著提升工作效率。用户可以自带AI API密钥，确保成本可控且数据安全。",2,"2026-06-11 03:50:12","high_star"]