The AI Safety Directory

Quality-scored directory of 102 ai safety tools, updated daily. Every tool scored on maintenance, adoption, maturity, and community signals.

Guardrails, content filtering, red teaming, and adversarial robustness tools — the safety layer between AI models and production deployment.

Verified

5

70–100

Established

10

50–69

Emerging

50

30–49

Experimental

37

10–29

Top tools by quality score

# Tool Score
1 BlackArch/blackarch

An ArchLinux based distribution for penetration testers and security researchers.

76
2 BishopFox/sliver

Adversary Emulation Framework

73
3 casdoor/casdoor

An open-source AI-first Identity and Access Management (IAM) /AI MCP & agent...

72
4 0xsyr0/Awesome-Cybersecurity-Handbooks

A huge chunk of my personal notes since I started playing CTFs and working...

71
5 openguardrails/openguardrails

Protect every action your agent takes.

70
6 Agent-Threat-Rule/agent-threat-rules

Open detection standard for AI agent threats. Like Sigma, but for prompt...

68
7 zan8in/afrog

A Security Tool for Bug Bounty, Pentest and Red Teaming.

67
8 globalbao/awesome-azure-policy

A curated list of blogs, videos, tutorials, code, tools, scripts, and...

63
9 Pantheon-Security/medusa

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and...

55
10 dapurv5/awesome-red-teaming-llms

Papers from our SoK on Red-Teaming (Accepted at TMLR)

54
11 IBM/ares

AI Robustness Evaluation System

54
12 The-Z-Labs/bof-launcher

bof-launcher - a library for loading, executing and in-memory masking BOFs...

54
13 H3llKa1ser/B00t2R00t

A penetration testing Swiss Army Knife that's suitable for CTF challenges,...

53
14 aisa-group/PostTrainBench

Measuring how well CLI agents like Claude Code or Codex CLI can post-train...

51
15 emmanuelgjr/GenAI-Security-Crosswalk

The most comprehensive open-source mapping of OWASP GenAI risks to industry...

50
16 microsoft/llmail-inject-challenge

Code for the API, workload execution, and agents underlying the...

49
17 microsoft/Test_Awareness_Steering

Code for the paper: Linear Control of Test Awareness Reveals Differential...

49
18 mensfeld/code-on-incus

Run coding agents in hardened Incus containers with real-time network threat...

49
19 skoveit/skovenet

Decentralized Adversary Emulation Framework

49
20 Shiritai/sanity-gravity

Providing a strong Gravity in the wild world of Antigravity (AI Agents), to...

48

Browse by category