DashClaw

ucsandman/DashClaw
β˜… 274 stars TypeScript AI/LLM Updated 1d ago
πŸ›‘οΈThe governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.
View on GitHub β†’ Try with Claude β€” $10 free β†’

Quick Install

Copy the config for your editor. Some servers may need additional setup β€” check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "dashclaw": {
      "command": "npx",
      "args": [
        "-y",
        "ucsandman/DashClaw"
      ]
    }
  }
}

README Excerpt

<div align="center"> <img src="public/images/logo-circular.png" alt="DashClaw" width="220" /> <h1>DashClaw</h1> <p><strong>Govern AI agents before they act.</strong></p> <p> DashClaw is the governance layer for AI agents that touch real systems. It sits between agents and the world, evaluates policy on every risky action,

Tools (5)

completedfailedlost_confirmationpartialpending

Topics

agent-frameworkagent-governanceagent-runtimeai-agentsai-governanceai-infrastructureai-opsautogenclaude-codecrew-aidecision-enginedeveloper-toolshermeslangchainmcp