Kits of AI agent skills, rules and prompts

Qwen3Guard-Stream-0.6B

Qwen · Kit

Checks text for safety token by token while a language model is still writing, rating each part safe, controversial or unsafe in 119 languages and dialects. Su…

Qwen3Guard-Gen-0.6B

Qwen · Kit

A small safety moderation model that labels a prompt or a model reply as safe, controversial or unsafe and names the risk categories, in 119 languages. Suits d…

gpt-oss-safeguard-20b

openai · Kit

Classifies text against a safety policy you write and shows its reasoning. For trust and safety teams filtering model inputs and outputs, labeling content onli…

gpt-oss-safeguard-120b

openai · Kit

Sorts text against a safety policy that you write, and shows its reasoning for each decision. It suits trust and safety teams that filter or label content.

phi-2

microsoft · Kit

A small text generation model that answers questions, continues chat dialogue and completes code. Made for researchers and developers who want a compact open m…

Mushroom_edibility_classifier

inigosarralde · Kit

Classifies mushroom pictures with a saved CNN model in a Gradio page, with the notebooks for scraping, training and the web app included. A learning project, n…

Obfuscated-Shell Safety Leaderboard

FINAL-Bench · Kit

Ranks language models on whether they see through disguised shell commands, blocking the dangerous ones and allowing harmless encoded ones. A defensive safety…

Safety Doesn't Translate

DhruvParmar051 · Kit

Shows side by side how Cohere's Tiny Aya answers before and after a safety repair that needs no retraining, using pre-judged replies from a test set. It suits…

ControlSpec — Before an agent acts

claytonsamples · Kit

Replays recorded tests of exact-action approval for AI agents, run through an NVIDIA OpenShell sandbox, so you can inspect approvals, replays and failures. For…

Z Image Turbo

Tongyi-MAI · Kit

A Gradio demo from Tongyi-MAI for its Z-Image-Turbo image model, tagged for MCP, with a prompt check and a safety checker model in its files. It suits designer…

Salamtak سلامتك

plitip · Kit

Checks one site photo for safety hazards and gives a Safe, Needs attention or Unsafe verdict with short alerts in seven worker languages. Runs on vision models…

SchemeArena

launch · Kit

Presents a research project that tests LLM agents for scheming across 400 scenarios, with a monitor called SCOUT. It is a static project page for AI safety res…

openpilot

commaai · Kit

comma.ai’s MIT-licensed driver assistance software for the cars on its supported list. It runs on a comma device in the car, or on a computer for development a…