#safety

GitHub Topic「safety」がついているAI関連リポジトリの集計。Topicはリポジトリ作者が自己申告するメタタグで、AI関連の文脈で何が「safety」と分類されているかを可視化します。

タグ付Repo

TOP6合計★

AIツール痕跡あり

TOP表示数

REPOS #safety のRepo (TOP 6 / Stars降順)

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 個人 1 sig 公開済 ↗

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 個人公開済 ↗

qchiujunhao/labcoat

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

Python ★ 0 AI 70 個人公開済 ↗

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 個人 1 sig 公開済 ↗