Orchestrate Your AI Agents.

The centralized control plane for AI coding tools. Manage Claude Code, Codex, Gemini, and OpenCode sessions across multiple servers.

Get Started Star on GitHub

# Start the control plane

$ ./cc-control -addr :18080 -admin-token $ADMIN_TOKEN

# Issue tenant tokens via Admin API

$ curl -X POST https://api.ac.dev/admin/tokens

# Connect an agent securely

$ ./cc-agent -control-url wss://api.ac.dev/ws/agent

# Agent connected. Ready to code.

$ _

Why Agent Control?

Multi-Server

One dashboard to rule them all. Manage diverse environments from a single pane of glass.

Secure by Design

Outbound-only WebSocket connections. No inbound ports. Zero Trust architecture ready.

Real-time PTY

Full xterm.js integration. It feels like SSH, but smarter and web-native.

Audit Trails

Every command, every output. Full JSONL logging for compliance and replay.

Native Apps

Control your agents on the go with dedicated macOS and iOS applications.

Open Source

MIT Licensed. Hackable. Deploy it on your own infrastructure.

Architecture

flowchart LR subgraph Clients Browser["Browser UI"] App["Native App"] end subgraph Control["Control Plane"] CC["cc-control"] end subgraph Agents A1["Agent 1"] A2["Agent 2"] end Clients -->|"REST/WS"| CC CC <-->|"Secure WS"| A1 CC <-->|"Secure WS"| A2 style Clients fill:#111,stroke:#333,color:#fff style Control fill:#111,stroke:#333,color:#fff style Agents fill:#111,stroke:#333,color:#fff style CC fill:#2563eb,stroke:#1d4ed8,color:#fff