使用 DashClaw 在代理和外部操作之间放置审批门禁和审计就绪的策略检查
Use DashClaw to intercept agent actions before they hit external systems, require approval or policy evaluation, and keep replayable decision evidence for later review.
Prerequisites
DashClaw service plus a supported agent framework or MCP-capable client
Installation
Use the upstream install or setup path that matches your environment:
- npx dashclaw-demo
- npm install dashclaw # or: pip install dashclaw
Requirements and caveats from upstream:
- Python uses the same shape with snake_case. Full reference: sdk/README.md. Step-by-step walkthrough: QUICK-START.md.
- Node SDK reference: canonical reference for the dashclaw npm package.
- Python SDK reference: same surface, snake_case.
Basic usage or getting-started notes:
- <p><sub>Plugs into the agents you already run: Claude Code, Codex, Hermes Agent, OpenClaw, Claude Desktop, and Claude Managed Agents. Framework integrations for LangChain, CrewAI, AutoGen, LangGraph, and OpenAI Agents...
- | Enforce | Declarative policies (risk thresholds, deploy gates, capability access rules, semantic checks) run on every action. |
- ### 10-second demo
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/ucsandman/DashClaw/HEAD/README.md
Documentation
- https://dashclaw.io/docs
```
