Claude Skill
ucsandman/DashClaw
DashClaw provides decision infrastructure for AI agents: intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails. Supports LangChain, AutoGen, CrewAI.
Overview
Stars275
Forks48
LanguageTypeScript
Last pushed2026-06-17
Last synced2026-06-17
Repository
Ownerucsandman
RepositoryDashClaw
Full nameucsandman/DashClaw
Repo ID1,152,532,642
GitHub URLhttps://github.com/ucsandman/DashClaw
Install this Skill
git clone https://github.com/ucsandman/DashClaw.gitRegistry
TypeUnknown
Quality scoreUnknown
VerificationUnknown
Last verifiedUnknown
Summary
DashClaw is a decision infrastructure for AI agents that intercepts actions, enforces guard policies, requires approvals, and produces audit-ready decision trails. It supports popular agent frameworks like LangChain, AutoGen, and CrewAI.
Chinese description
🛡️AI代理的决策基础设施。拦截操作、执行防护策略、要求审批，并生成符合审计要求的决策轨迹。
Key features
- Intercept agent actions in real-time
- Enforce customizable guard policies
- Require human or automated approvals
- Generate audit-ready decision trails
- Integrates with LangChain, AutoGen, CrewAI
Use cases
- Govern AI agent behavior in production
- Enforce compliance and safety policies
- Enable human-in-the-loop approval workflows
- Audit agent decisions for regulatory requirements