Belay is an open-source, local-first security layer for AI coding agents (Claude Code, Codex, Cursor, OpenClaw, Hermes Agent and MCP) that blocks dangerous commands, secret leaks, and prompt injection at the tool-call boundary in under 100ms — no LLM in the decision path by default, no cloud, no phone-home.
- advisory code analysis flagged committed secret in SECBLOK/belay
- new_repo new repo SECBLOK/belay
- release gh release SECBLOK/belay v0.1.14
- release gh release SECBLOK/belay v0.1.13
- release gh release SECBLOK/belay v0.1.0
j down k up gg top G end