Orchestrate AI coding agents. Ship code faster.
Run and coordinate Claude Code, Codex CLI, Gemini CLI, Aider and more — from a single platform.
Website · Docs · Quick Start · Discord · LinkedIn
AgentsMesh is an AI Agent Fleet Command Center — a platform that enables teams to run, manage, and coordinate AI coding agents at scale.
Instead of running agents one-at-a-time on your local machine, AgentsMesh lets you spin up remote AI workstations (AgentPods), orchestrate multi-agent collaboration through channels and pod bindings, and track everything via integrated task management — all from a single web console.
BYOK (Bring Your Own Key) — You provide your own AI API keys. No usage caps. Full cost control.
- AgentPod — Remote AI workstations with web terminal, Git worktree isolation, and real-time streaming. Run multiple concurrent pods.
- Multi-Agent Collaboration — Coordinate agents through channels and pod bindings. Visualize the collaboration topology in real-time.
- Task Management — Kanban board with ticket-pod binding, progress tracking, and MR/PR integration.
- Self-Hosted Runners — Deploy runners on your own infrastructure. Your code never leaves your environment.
- Multi-Agent Support — Claude Code, Codex CLI, Gemini CLI, Aider, OpenCode, and any custom terminal-based agent.
- Multi-Git Provider — GitLab, GitHub, and Gitee integration.
- Multi-Tenant — Organization > Team > User hierarchy with row-level isolation.
- Enterprise Ready — SSO, RBAC, audit logs, air-gapped deployment support.
The fastest way to use AgentsMesh is through our hosted service at agentsmesh.ai — sign up, connect your Git provider, and start running agents in minutes.
The Runner is a lightweight daemon that runs on your machine and executes AI agents locally. Your code stays on your infrastructure.
curl -fsSL https://agentsmesh.ai/install.sh | shOr via Homebrew:
brew install agentsmesh/tap/agentsmesh-runnerSee the Runner README for more installation options (deb, rpm, Windows, etc.)
agentsmesh-runner loginThis opens your browser to authenticate. For headless environments (SSH, remote server):
agentsmesh-runner login --headlessFor self-hosted deployments, add --server:
agentsmesh-runner login --server https://your-server.comagentsmesh-runner runOr install as a system service for always-on operation:
agentsmesh-runner service install
agentsmesh-runner service startOnce the runner is online, create an AgentPod from the web console and start coding with your AI agents.
AgentsMesh separates control plane from data plane — orchestration commands travel through gRPC with mTLS, while terminal I/O streams through a Relay cluster.
| Component | Description |
|---|---|
| Backend | Go API server — auth, org/team management, pod lifecycle, task management |
| Web | Next.js frontend — dashboard, web terminal, kanban, topology visualization |
| Relay | Terminal relay cluster — low-latency WebSocket pub/sub between runners and browsers |
| Runner | Self-hosted Go daemon — connects to Backend (gRPC+mTLS) and Relay (WebSocket), runs AI agents in isolated PTY sandboxes |
| Web-Admin | Internal admin console — user/org/runner management, audit logs |
git clone https://github.com/AgentsMesh/AgentsMesh.git
cd AgentsMesh/deploy/dev
./dev.shThis starts the full stack: PostgreSQL, Redis, MinIO, Backend, Relay, Traefik, and a local Next.js frontend with hot reload.
Access:
| Service | URL |
|---|---|
| Web Console | http://localhost:3000 |
| API | http://localhost:80/api |
Test Accounts:
| Role | Password | |
|---|---|---|
| User | dev@agentsmesh.local | devpass123 |
| Admin | admin@agentsmesh.local | adminpass123 |
Ports are dynamically allocated per worktree. Check
deploy/dev/.envfor actual values.
Manual Setup
Prerequisites: Go 1.24+, Node.js 20+, pnpm, Docker
# 1. Start infrastructure
cd deploy/dev && ./dev.sh
# 2. Backend (auto-starts in Docker with hot reload)
docker compose logs -f backend
# 3. Frontend (local with Turbopack)
cd web && pnpm install && pnpm devProduction Deployment
Docker images are published to Docker Hub on every push to main:
agentsmesh/backend:sha-xxxxxxx
agentsmesh/web:sha-xxxxxxx
agentsmesh/web-admin:sha-xxxxxxx
agentsmesh/relay:sha-xxxxxxx
Tagged releases (v*) get semver tags:
agentsmesh/backend:1.0.0
agentsmesh/backend:1.0
See deploy/selfhost/ for self-hosted deployment guide.
| Agent | Provider | Description |
|---|---|---|
| Claude Code | Anthropic | Autonomous AI coding agent |
| Codex CLI | OpenAI | OpenAI's code generation CLI |
| Gemini CLI | Google Gemini CLI | |
| Aider | Open Source | AI pair programming in the terminal |
| OpenCode | Open Source | Open source AI coding tool |
| Custom | Any | Any terminal-based agent |
| Layer | Technology |
|---|---|
| Backend | Go (Gin + GORM) |
| Frontend | Next.js (App Router) + TypeScript + Tailwind CSS |
| Database | PostgreSQL + Redis |
| Storage | MinIO (S3-compatible) |
| API | REST + gRPC (bidirectional streaming) |
| Security | mTLS for runner connections, JWT for web auth |
| Real-time | gRPC streaming (Runner ↔ Backend), WebSocket (Relay ↔ Browser) |
| Reverse Proxy | Traefik |
AgentsMesh/
├── backend/ # Go API server
├── web/ # Next.js frontend
├── web-admin/ # Admin console (Next.js)
├── runner/ # Self-hosted runner daemon (Go)
├── relay/ # Terminal relay server (Go)
├── proto/ # Protocol Buffers definitions
├── ci/ # CI Dockerfiles
├── deploy/
│ ├── dev/ # Docker Compose dev environment
│ └── selfhost/ # Self-hosted deployment guide
└── docs/ # Architecture docs and RFCs
We welcome contributions! See CONTRIBUTING.md for guidelines.
Business Source License 1.1 (BSL-1.1)
- Change Date: 2030-02-28
- Change License: GPL-2.0-or-later
The 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 for the full terms and additional use grant.
