AgentsMesh

Where teams scale beyond headcount.

The AI Agent Workforce Platform. Run a hundred AI agents across your own machines — and command them all from one console.

Website · Docs · Quick Start · Discord · X · X (founder) · LinkedIn

---

The problem: one operator, a hundred agents

AI coding agents have made individual engineers wildly productive — but individual productivity has a ceiling. The next 10x isn't a smarter agent; it's running many agents at once, and directing them like a team.

That ambition breaks the moment you try it for real:

• A hundred agents won't fit on one laptop.
• Nobody can babysit a hundred terminals.
• Each agent needs its own clean, isolated workspace — or they corrupt each other's state.
• Long-running agents stall, get stuck, and silently die.
• Agents working in isolation never compound into a team.

What's missing isn't the agent. It's the control layer that turns one operator into the director of an agent workforce — the layer that schedules agents onto machines, isolates them, keeps them alive, lets them collaborate, and puts all of it on one screen.

AgentsMesh is that layer.

From problem to platform

Every part of AgentsMesh exists to answer one question: how does a single person reliably run, watch, and steer a hundred agents? Each capability is the direct answer to a wall you hit when you scale.

The wall you hit	What AgentsMesh gives you
100 agents won't run on one machine	Runner fleet — install self-hosted runners across any number of machines. Each advertises its capacity (max_concurrent_pods), and agents are scheduled onto the runner you pick or an available one from the pool. Your code never leaves your infrastructure.
Every agent needs a clean, isolated environment	Workspace isolation — each agent runs in its own pod with a dedicated Git worktree sandbox (sandboxes/{pod}/workspace/), private credentials, and its own branch. Concurrent agents never step on each other.
You can't watch a hundred terminals	One console, every screen — Web, Desktop (Electron), and iOS (SwiftUI) clients, all driven by the same Rust core. Paginated pod sidebar, multi-pane workspace, and real-time terminal streaming let one person hold many agents in view.
Long-running agents stall and need babysitting	Autopilot — a control agent watches a pod and sends the next instruction the moment it goes idle, with iteration caps, decision history, and human takeover/handback. Self-healing, unattended runs.
Agents working alone don't compound	Mesh & Channels — bind pods together, let them talk over channels with @mentions, and watch the collaboration topology update in real time.

The rest is plumbing built so that chain holds up under load: a control-plane / data-plane split — orchestration over gRPC with mTLS, terminal bytes over a stateless Relay cluster — so the backend never bottlenecks on PTY traffic, no matter how many agents are streaming at once.

Core concepts