CTRLRun

Organization

@ctrlrun

The execution safety layer for AI agents. A consequential action happens at most once, exactly as approved, and leaves a receipt.

United States of America ctrlrun.dev/ On GitHub since September 2026

Published Tools

Total Stars

Weekly Downloads

GitHub Followers

Public Repos

Published Tools

3 Agentsacross 2 categories

Make consequential AI-agent actions safe to execute.

AgentSecurity

274 dirs

Route a CTRLRun APPROVE through the OpenAI Agents SDK's tool-approval interruption.

Agentai-agents

1 dir

Gate a LangChain agent's tool calls with a CTRLRun policy, through wrap_tool_call.

Agentai-agents

1 dir