Git Stars Git Stars

#safety Repositories

Discover 25 active open source GitHub repositories tagged with #safety, accumulating 46,185 total stars (averaging 1,847 stars per project). Leading this topic is NVIDIA-NeMo/Guardrails with 7,539 stars.

25
Total Repositories
46,185
Total Stars
1,847
Avg Stars/Repo
1
NVIDIA-NeMo/Guardrails

NeMo Guardrails is an open-source library for applying programmable safety and security controls to LLM and agentic applications.

NVIDIA-NeMo
โญ 7,539 Python ๐Ÿ‘ค NVIDIA-NeMo Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2023-04-18
2
millsp/ts-toolbelt

๐Ÿ‘ท TypeScript's largest type utility library

millsp
โญ 7,141 TypeScript ๐Ÿ‘ค millsp User ๐Ÿ• Updated 2025-06-02 ๐Ÿ“… Created 2019-06-08
3
Dicklesworthstone/destructive_command_guard

A fast Rust safety hook that blocks destructive shell, git, and filesystem commands before AI coding agents run them. 50+ security packs (databases, Kubernetes, Docker, cloud, Terraform), heredoc/inline-script scanning, CI scan mode, and explain mode; works with Claude Code, Codex, Gemini, Copilot, Cursor, and more.

Dicklesworthstone
โญ 6,372 Rust ๐Ÿ‘ค Dicklesworthstone User ๐Ÿ• Updated 2026-11-17 ๐Ÿ“… Created 2026-01-07
4
cncf/tag-security

๐Ÿ”CNCF Security Technical Advisory Group -- secure access, policy control, privacy, auditing, explainability and more!

cncf
โญ 2,248 HTML ๐Ÿ‘ค cncf Organization ๐Ÿ• Updated 2025-12-08 ๐Ÿ“… Created 2018-03-13
5
CryptoAILab/Awesome-LM-SSP

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

CryptoAILab
โญ 2,106 ๐Ÿ‘ค CryptoAILab Organization ๐Ÿ• Updated 2026-09-02 ๐Ÿ“… Created 2024-01-09
6
yueliu1999/Awesome-Jailbreak-on-LLMs

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

yueliu1999
โญ 2,034 ๐Ÿ‘ค yueliu1999 User ๐Ÿ• Updated 2026-11-08 ๐Ÿ“… Created 2024-06-27
7
PKU-Alignment/safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

PKU-Alignment
โญ 1,624 Python ๐Ÿ‘ค PKU-Alignment Organization ๐Ÿ• Updated 2025-11-24 ๐Ÿ“… Created 2023-05-15
8
stanislaw/awesome-safety-critical

List of resources about programming practices for writing safety-critical software.

stanislaw
โญ 1,588 Python ๐Ÿ‘ค stanislaw User ๐Ÿ• Updated 2025-03-11 ๐Ÿ“… Created 2017-03-02
9
omegaee/my-fingerprint

Protect Your Browser Fingerprints | Protect Your Browser Fingerprints | Chrome, Edge, Firefox | Extension / Extension

omegaee
โญ 1,506 TypeScript ๐Ÿ‘ค omegaee User ๐Ÿ• Updated 2026-11-08 ๐Ÿ“… Created 2023-11-01
10
mpusz/mp-units

The Domain-Correct Quantities and Units Library for C++ โ€” full quantity kind safety, ISO 80000 compliant, C++29 standardization candidate.

mpusz
โญ 1,500 C++ ๐Ÿ‘ค mpusz User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2018-08-22
11
nette/latte

โ˜• Latte: the safest & truly intuitive templates for PHP. Engine for those who want the most secure PHP sites.

nette
โญ 1,296 PHP ๐Ÿ‘ค nette Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2012-06-20
12
thu-coai/Safety-Prompts

Chinese safety prompts for evaluating and improving the safety of LLMs. Chinese safety prompts, used to evaluate and enhance the safety of large models.

thu-coai
โญ 1,121 ๐Ÿ‘ค thu-coai Organization ๐Ÿ• Updated 2024-02-27 ๐Ÿ“… Created 2023-04-18
13
THU-BPM/MarkLLM

[EMNLP 2024 Demo] MarkLLM: An Open-Source Toolkit for LLM Watermarking

THU-BPM
โญ 1,093 Python ๐Ÿ‘ค THU-BPM Organization ๐Ÿ• Updated 2026-09-05 ๐Ÿ“… Created 2024-05-16
14
disclose/diodb

Open-source vulnerability disclosure and bug bounty program database

disclose
โญ 1,083 Python ๐Ÿ‘ค disclose Organization ๐Ÿ• Updated 2026-11-09 ๐Ÿ“… Created 2018-05-17
15
SafeAI-Lab-X/ClawKeeper

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka The Norton for OpenClaw)

SafeAI-Lab-X
โญ 1,020 TypeScript ๐Ÿ‘ค SafeAI-Lab-X User ๐Ÿ• Updated 2026-08-17 ๐Ÿ“… Created 2026-03-20
16
learnsyslab/safe-control-gym

PyBullet CartPole and Quadrotor environmentsโ€”with CasADi symbolic a priori dynamicsโ€”for learning-based control and RL

learnsyslab
โญ 937 Python ๐Ÿ‘ค learnsyslab Organization ๐Ÿ• Updated 2026-04-29 ๐Ÿ“… Created 2021-08-04
17
jxzhangjhu/Awesome-LLM-Uncertainty-Reliability-Robustness

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

jxzhangjhu
โญ 840 ๐Ÿ‘ค jxzhangjhu User ๐Ÿ• Updated 2026-11-07 ๐Ÿ“… Created 2023-03-20
18
chauncygu/Safe-Reinforcement-Learning-Baselines

The repository is for safe reinforcement learning baselines.

chauncygu
โญ 816 Jupyter Notebook ๐Ÿ‘ค chauncygu User ๐Ÿ• Updated 2026-03-13 ๐Ÿ“… Created 2022-02-22
19
sefinek/Sefinek-Blocklist-Collection

๐ŸŒ A repository of blocklists for various DNS servers, featuring over 100 links and more than 6 million domains. Additionally, you can use our personalized Blocklist Generator to customize content filtering according to your individual needs, giving you full control over what should be blocked on your network.

sefinek
โญ 779 JavaScript ๐Ÿ‘ค sefinek User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2022-09-01
20
phpstan/phpstan-strict-rules

Extra strict and opinionated rules for PHPStan

phpstan
โญ 716 PHP ๐Ÿ‘ค phpstan Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2017-11-11
21
bao-project/bao-hypervisor

Bao, a Lightweight Static Partitioning Hypervisor

bao-project
โญ 595 C ๐Ÿ‘ค bao-project Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2020-01-10
22
globocom/huskyCI

Performing security tests inside your CI

globocom
โญ 588 Go ๐Ÿ‘ค globocom Organization ๐Ÿ• Updated 2024-05-15 ๐Ÿ“… Created 2018-06-20
23
arthurfiorette/prisma-json-types-generator

โš’๏ธ Changes JsonValues to your custom typescript type.

arthurfiorette
โญ 570 TypeScript ๐Ÿ‘ค arthurfiorette User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2023-01-06
24
Alejandros17487/ai-jailbreaks

AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models โ€” system prompts, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing.

Alejandros17487
โญ 559 ๐Ÿ‘ค Alejandros17487 User ๐Ÿ• Updated 2026-10-21 ๐Ÿ“… Created 2026-10-21
25
nette/forms

Generating, validating and processing secure forms in PHP. Handy API, fully customizable, server & client side validation and mature design.

nette
โญ 531 PHP ๐Ÿ‘ค nette Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2013-11-28

Frequently Asked Questions

1

What is the most popular #safety repository on GitHub?

The top ranked open source #safety project on GitHub is NVIDIA-NeMo/Guardrails with 7,539 stars. NeMo Guardrails is an open-source library for applying programmable safety and security controls to LLM and agentic applications.

2

Which programming languages are most used in #safety repositories?

Among the top ranked #safety projects on GitHub, the most common programming languages are Python, TypeScript, PHP, Rust.

3

How is the #safety repository ranking calculated?

We track 25 active open source repositories tagged with #safety (500+ stars), totaling 46,185 stars with an average of 1,847 stars per repository. Rankings update daily from the GitHub API.