Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
- golang
- observability
- opentelemetry
- policy-engine
Repository Index
47,133 repositories indexed
1–3 of 3 · Most stars
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Inline review tool for MDXG markdown — capture highlighted comments and export them as structured JSON for LLM agents.
- annotations
- feedback
- human-in-the-loop
- inline-comments