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.
Guardrails, PII redaction, prompt-injection defense, interpretability and offensive/defensive AI security.
Signals: ai-safety, ai-security, guardrails, prompt-injection, jailbreak, llm-security, interpretability, explainable-ai
374 results
SPECA: Specification-to-Checklist Agentic Auditing Framework
SAF-MCP is a comprehensive security framework for documenting and mitigating threats in the AI Agent ecosystem.
Nova-Proximity is a MCP and Agent Skills security scanner powered with NOVA
Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds secure-by-default practices into AI coding workflows (generation and review). It ships core security rules, translators for popular coding agents, and validators to test rule compliance.
Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall isolation for Linux and macOS
A native policy enforcement layer for AI coding agents. Built on OPA/Rego.
Mirrored snapshot of Claude Code's source (exposed 2026-03-31) preserved for educational purposes, defensive security research, and software supply-chain analysis.
降低学术论文 AIGC 查重率的 Claude Code Skill | A Claude Code skill for reducing AIGC detection rates in academic papers
Lasso security integrations for Claude Code, including prompt-injection defenses
Cybersecurity skills for AI coding agents (Claude Code, Cursor, Codex)
Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, and 20+ language-specific security quirks.
No description
No description
Claude Code 逆向工程研究仓库
SeClaw provides a practical foundation for measuring, diagnosing, and comparing security failures in autonomous LLM agents.
LLM privacy gateway in Go — millisecond-latency PII and secret redaction. Used in production by PackyCode.
Powerful search page powered by LLMs and SearXNG
The automated prompt injection framework for LLM-integrated applications.
Redteaming LLMs using other LLMs
Dropbox LLM Security research code and results
AI / LLM Red Team Field Manual & Consultant’s Handbook
AI-native automated software risk analysis skill. LLM-driven, Code-First approach for comprehensive security risk assessment, threat modeling, security testing, penetration testing, and compliance checking.
Open-source LLM red-teaming technique toolkit (162 transforms, 36 mutators, 25 tool surfaces). MIT.
Lightweight LLM firewall: masks PII, routes calls, leaves zero trace.
24,535 repositories in the index in total.
