Collection

AI Safety & Alignment

The AI Safety & Alignment collection tracks 14 curated open-source projects, 0 of them live on TrendingRepo right now — ranked by a cross-source momentum score blending GitHub star velocity with mentions on Hacker News, X, Bluesky, Product Hunt and Dev.to.

Live · top 14 repos · sorted by momentum across 24H

STALE · 16d

Velocity period:24h 7d 30dClick to re-sort top 14

#	Repository	24h	7d	30d
01	fairlearn/fairlearn No description published.	—	—	—
02	guardrails-ai/guardrails No description published.	—	—	—
03	llm-attacks/llm-attacks No description published.	—	—	—
04	meta-pytorch/captum No description published.	—	—	—
05	microsoft/presidio No description published.	—	—	—
06	microsoft/responsible-ai-toolbox No description published.	—	—	—
07	NVIDIA-NeMo/Guardrails No description published.	—	—	—
08	NVIDIA/garak No description published.	—	—	—
09	openai/evals No description published.	—	—	—
10	openai/safety-gym No description published.	—	—	—
11	protectai/llm-guard No description published.	—	—	—
12	shap/shap No description published.	—	—	—
13	Trusted-AI/AIF360 No description published.	—	—	—
14	Trusted-AI/AIX360 No description published.	—	—	—

Showing 14 of 14 · ranked by momentum, velocity, and consensus

Prev Next