Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A curated list of public-source, research, and commercial tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, LLM red-teaming, and more.
| Date | Stars |
|---|---|
| 2026-07-31 | 926 |
| 2026-08-01 | 937 |
| 2026-08-06 | 937 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome AI Security Tools [](https://awesome.re) > A curated list of **public-source, research, and commercial** tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, LLM red-teaming, and more. [](https://creativecommons.org/publicdomain/zero/1.0/) [](#contributing) **Type legend:** 🟢 public source / open-source · 🔬 research (paper / benchmark / dataset / framework) · 🟠 commercial with open components · ⚠️ restrictive, non-commercial, or unclear/no license — check before use. GitHub-hosted entries show static **★ stars** and **last-commit** snapshots; refresh them with `python3 scripts/update_github_metrics.py` before release. Latest snapshot: 2026-08-01. Hugging Face model entries show license, access, and artifact metadata. Ordering within a section favors flagship and actively maintained projects. --- ## Contents - [Autotriage of Security Findings](#autotriage-of-security-findings) - [AI Agent & Coding-Agent Security](#ai-agent--coding-agent-security) - [Scanners & Auditors](#scanners--auditors) - [Frameworks, Rule Standards & Benchmarks](#frameworks-rule-standards--benchmarks) - [Runtime Protection & Enforcement](#runtime-protection--enforcement) - [AI/ML Supply Chain & Model Security](#aiml-supply-chain--model-security) - [Pentest & Red-Team Agents](#pentest--red-team-agents) - [AI-Powered Recon & Narrow ML Tools](#ai-powered-recon--narrow-ml-tools) - [Subdomain & DNS Prediction](#subdomain--dns-prediction) - [Recon Screenshot Triage](#recon-screenshot-triage) - [Software / Tech Fingerprinting](#software--tech-fingerprinting) - [AI-Assisted Fuzzing](#ai-assisted-fuzzing) - [Password / Credential ML](#password--credential-ml) - [Phishing Detection (Visual / URL)](#phishing-detection-visual--url) - [AI/ML-Assisted Detection Rules & Engines](#aiml-assisted-detection-rules--engines) - [Defensive Trained-Model Detectors](#defensive-trained-model-detectors) - [AI-Powered SAST & Secure Code Review](#ai-powered-sast--secure-code-review) - [LLM-Driven Fuzzing](#llm-driven-fuzzing) - [Harness / target generation](#harness--target-generation) - [Fuzzing the LLM](#fuzzing-the-llm) - [Threat Intelligence](#threat-intelligence) - [Log Analysis / SIEM / SOC Triage](#log-analysis--siem--soc-triage) - [Reverse Engineering](#reverse-engineering) - [LLM Red-Teaming & Guardrails](#llm-red-teaming--guardrails) - [Scanners, Evals & Guardrails](#scanners-evals--guardrails) - [Prompt-Injection Classifier Models](#prompt-injection-classifier-models) - [Specialty Security LLMs](#specialty-security-llms) - [LLM Honeypots & Deception](#llm-honeypots--deception) - [CTF / Exploit / Bug-Bounty Agents & Benchmarks](#ctf--exploit--bug-bounty-agents--benchmarks) - [Cloud / IaC / DFIR / OSINT / Phishing](#cloud--iac--dfir--osint--phishing) - [Related Awesome Lists](#related-awesome-lists) - [Contributing](#contributing) - [Contact](#contact) - [License](#license) --- ## Autotriage of Security Findings AI/LLM tools that triage, deduplicate, prioritize, or validate the output of scanners and finding sources. - **[nuclei-autotriage](https://github.com/cyberok-org/nuclei-autotriage)** 🟢⚠️ — Two-stage LLM triage (falsifier + red-team pass) of Nuclei JSONL findings via OpenAI-compatible endpoints (vLLM/Ollama). *(CyberOK)* — **note:** restrictive personal/non-commercial EULA, not a permissive OSS license. *(★ 1 · updated 2026-05-25)* - **Related:** [agent-audit](https://github.com/scadastrangelove/agent-audit) · [asamm](https://github.com/scadastrangelove/asamm) - **[seclab-taskflow-agent](https://github.com/GitHubSecurityLab/seclab-taskflow-agent)** 🟢 — YAML-driven taskflo
Excerpt of 98,176 characters
Read on GitHub
50
3
Shaked Zin · @cynative
1
morluto
1
1
1
1
1
1
1
1
1
1
1
1
1
Armorer · @ArmorerLabs
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c94b87a48cd36e13, topic:awesome, topic:awesome-list, desc:curated list
matched fp:c94b87a48cd36e13, topic:agents, topic:agentic-ai