#safety

GitHub repositories that have self-applied the topic "safety" — a creator-tagged metadata that surfaces how AI projects describe themselves.

tagged repos

top 6 stars

with tool sigs

shown

REPOS Repos for #safety (top 6 by stars)

Noumenon-ai/AutoMaxFix

A reliability layer for AI-built systems: detect failures (tests or runtime drift), reproduce, repair one ticket at a time behind an approval gate, and prove the fix. The safety boundaries most AI agents skip.

Python ★ 3 AI 70

dhotherm/mdx-rust

Rust-native optimizer for LLM agents. Policy-driven experimentation with safe, compile-validated edits.

Rust ★ 2 AI 70 Solo 1 sig live ↗

GurthBro0ks/slimeOS

🐌 SlimyOS Habitat — A supervised autonomous Linux control plane. Policy engine, tool broker, proof packs, panic stop, failure memory. Agents can't misbehave.

Python ★ 0 AI 70

santicalderon/burnstop

Pre-flight budget gate for AI agent runaways. Drop-in. Hard-stop before token-1. LangChain · LangGraph · AutoGen · CrewAI

Python ★ 0 AI 70 Solo live ↗

qchiujunhao/labcoat

Skills, hooks, and CLI checks for safer biomedical AI coding agents.

Python ★ 0 AI 70 Solo live ↗

copyleftdev/kitboga

Defensive Claude Code scam-baiting agent harness with personas, stall tactics, anti-detection, session state, intel extraction, and call QA.

HTML ★ 0 AI 60 Solo 1 sig live ↗