AgentsMesh
An AI coding agent orchestration platform coordinates Claude Code, Codex CLI and other agents on your own runners, with hosted or private deployment.

AgentsMesh coordinates AI coding agents across local machines and servers for developers managing concurrent work. A shared console lets teams assign tasks, watch terminals and follow progress across agents.
- Isolated workspaces: Each agent gets its own Git worktree, branch and credentials, so agents can work concurrently in separate environments.
- Agent collaboration: Agents observe each other's terminals, exchange context through channels and find or recruit peers for a task.
- Tickets and reviews: A Kanban board links tasks to agent work, branches and pull or merge requests, with live CI status.
- Scheduled work: Agents can handle recurring reviews, dependency updates, security scans and test runs, with logs, diffs and Slack or webhook alerts; workflows can chain multiple agents.
- Autopilot: A control agent supplies follow-up instructions when a coding agent becomes idle, with iteration limits, decision history and human takeover.
Supported agents include Claude Code, Codex CLI, Gemini CLI, Aider, OpenCode, Cursor CLI and custom terminal-based agents. Browser, desktop and iOS clients provide access to the console.
The paid hosted service supplies the control platform while self-hosted runners execute agents and hold working copies on your infrastructure. Hosted orchestration relays terminal output over encrypted connections. Private deployments support Docker, Kubernetes and air-gapped environments. You supply your own AI API keys; model access and data sent to providers depend on the agents you choose.