AgentsMesh
AI coding agent orchestration with self-hosted runners, isolated workspaces, and a shared console for Claude Code, Codex CLI, Aider, and custom agents.
AgentsMesh coordinates AI coding agents across your own machines for developers and teams managing concurrent work. Runners execute agents on local hardware or servers you control, while a shared console lets you assign tasks and follow progress. The paid hosted service provides the control platform; private deployments support Docker, Kubernetes, and air-gapped environments. You bring your own AI API keys, so model access depends on the agents and providers you use.
Each agent gets an isolated workspace with its own Git worktree, branch, and credentials. Agents can watch each other's terminals, exchange context in channels, find collaborators, and recruit other agents for a task. Supported tools include Claude Code, Codex CLI, Gemini CLI, Aider, OpenCode, and Cursor CLI, alongside custom terminal-based agents. You can monitor work through browser, desktop, and iOS clients.
Tickets connect a Kanban board to agent work, branches, and pull or merge requests, with live CI status and progress tracking. Scheduled tasks cover code reviews, dependency updates, security scans, and test runs, with logs, diffs, and Slack or webhook alerts. Multi-step workflows can chain agents together. Autopilot watches for idle agents and supplies follow-up instructions, with iteration limits and human takeover. Runners keep working copies on your infrastructure; the hosted platform handles orchestration and relays terminal output over encrypted connections.
