ucsandman/DashClaw
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.
Sits as a middleware layer between agents and external systems, evaluating declarative guard policies with pre-execution interception. Supports multiple SDKs (Node.js/Python), framework integrations (LangChain, CrewAI, Claude Code, OpenAI Agents SDK), and includes real-time approval queues with behavioral drift detection via statistical analysis of agent assumptions.
121 stars. Available on npm.
Stars
121
Forks
23
Language
JavaScript
License
MIT
Category
Last pushed
Mar 14, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/ucsandman/DashClaw"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Compare
Related agents
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and...
mattijsmoens/sovereign-shield
AI security framework: tamper-proof action auditing, prompt injection firewall, ethical...
vstorm-co/pydantic-ai-middleware
Middleware layer for Pydantic AI — intercept, transform & guard agent calls with 7 lifecycle...
vstorm-co/pydantic-ai-shields
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII...
Dicklesworthstone/destructive_command_guard
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being...