AI Security: open-source projects on GitHub
56 repositories on AI Security, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
SKILLSPECTOR: AGENT PROTECTION
Scanner searches for vulnerabilities, prompt injections, and data leaks in Claude Code, Codex, and MCP skills before installation.
★ 26,146 · PythonCODEX-SECURITY CODE PROTECTION
CLI and TypeScript SDK for finding, checking, and fixing vulnerabilities in code, based on OpenAI Codex.
★ 13,590 · TypeScriptAI Bug Hunter
A set of tools for finding vulnerabilities, powered by AI and available without a subscription.
★ 5,900 · PythonGISKARD-OSS - LLM AGENT EVALUATION
Library for evaluating and testing LLM agents with open-source code.
★ 5,417 · PythonOPEN SOURCE RED TEAMING TOOLKIT FOR AI
Open-source toolkit from Microsoft for finding security and safety vulnerabilities in generative AI systems. Automates scanning, adaptive multi-turn attacks, and manual t
★ 4,966 · PythonClaude Code: All Levels
Complete guide to Claude Code from basics to advanced scenarios — templates, agent workflows, tests, and cheat sheet for maximum productivity.
★ 4,357 · TypeScriptAI SYSTEM SECURITY
A platform for testing the security of AI ecosystems: scanning infrastructure, MCP, agents, and evaluating jailbreak attacks.
★ 3,790 · PythonKritt AI: Vulnerability Detection
Open-source tool for self-hosting that uses AI agents to automatically detect and confirm vulnerabilities in source code.
★ 2,431 · JavaScriptCapability-based sandbox proxy
Capability-based sandboxes with fine-grained policy. Proxy access directly in the agent's execution context, with zero configuration and zero latency.
★ 2,407 · RustTOP AI CODING ASSISTANTS
Collected over 2000 stars, a list of the best AI tools for code generation, autocomplete, and refactoring. Supports popular languages and IDE integrations.
★ 2,287ADR: AI Agent Security in Uber
ADR provides observability, security testing, and threat detection for enterprise AI agents, already used at Uber.
★ 2,135 · PythonBug Hunter
Autonomous vulnerability hunting in the terminal: reconnaissance, 20 vulnerability classes, report generation, all inside Claude Code.
★ 2,064 · PythonToolHive: Manage MCP Servers
ToolHive is an enterprise platform written in Go for launching and managing Model Context Protocol (MCP) servers in corporate environments.
★ 1,842 · GoAI-AGENT FOR SECURITY
0 — open-source AI security agent that autonomously detects, exploits and fixes vulnerabilities in the stack. Research preview from Swiss Applied AI & Cybersecurity Resea
★ 1,356 · TypeScriptXALGORIX AI Pentest Agents
Autonomous AI agents for pentesting: reconnaissance, vulnerability discovery, and exploitation in real time. Implemented in Go and TypeScript.
★ 1,355 · GoATTACKGEN: AI INCIDENT RESPONSE
Generates realistic cyberattack scenarios using LLM and MITRE ATT&CK, tailored to your organization and selected threat groups.
★ 1,275 · PythonAUTOCVE — AGENT SCANS CODE
An AI‑agent‑based automated platform for finding CVEs in source code, verifying vulnerabilities, and generating reports.
★ 1,226 · PythonSTRIDE GPT Threat Modeling AI
A strategic tool for automatically generating threat models using the STRIDE methodology with OpenAI's GPT.
★ 1,157 · PythonAI Agent for Pentesting
The project turns Claude Code into a research assistant for authorized pentesting, offering specialized AI subagents that plan engagements, analyze reconnaissance data, r
★ 1,124 · ShellPENTESTCODE: AI PENTEST SYSTEM
Autonomous multi-agent TypeScript system for penetration testing with engagement state and parallel execution.
★ 1,055 · TypeScriptMEDUSA: AI Security Scanner
AI-first scanner with 79 analyzers and 40,000+ threat detection rules for AI/ML, LLM agents, and MCP servers.
★ 1,018 · PythonPIPELOCK PROTECTS AI AGENTS
AI agent firewall for MCP security and egress traffic. Scans HTTP, MCP, A2A and WebSocket traffic in real time for exfiltration, SSRF and prompt injection, emitting media
★ 993 · GoSHIP-SAFE SECURITY AGENTIC
The ship-safe CLI scanner looks for CI/CD vulnerabilities, agent permission risks, MCP injections, secrets, and dependencies flagged by DMCA.
★ 872 · JavaScriptThinkWatch: AI Bastion Host
Enterprise bastion for secure access to AI API and MCP with unified proxy service, RBAC, audit, rate limiting, and cost tracking. Supports OpenAI, Anthropic, Gemini, and
★ 868 · RustClaude-BugHunter - Bug Hunt
51 skills, 15 slash commands and 574+ report templates for bug hunting and red-team work.
★ 786 · PythonARCJET: AI SECURITY
Protect your AI agents from prompt injections, data theft, and tool abuse with a simple TypeScript module.
★ 701 · TypeScriptAI firewall for MCP
Open AI-agent firewall for MCP protection: outbound request control, DLP, SSRF and prompt injection defense.
★ 636 · GoAPI RELAY SECURITY SCANNER
Local scanner for AI API relays and LLM proxies. 620 ⭐ on GitHub.
★ 620 · PythonAGENT OPFOR ATTACK EMULATION
Open‑source framework for simulating attacks on AI agents and MCP servers. Written in TypeScript and already has 377⭐.
★ 586 · TypeScriptEMILIA PROTOCOL ACTION GUARDIAN
EMILIA Gate verifies authority before changing money, code, permissions, and infrastructure, providing independently verifiable proof.
★ 550 · TypeScriptAI-Powered Pentest Tool
An offensive-security MCP server featuring 205 tools, 17 agents, and 60 probes for OWASP Top 10.
★ 514 · PythonAGENT-SKILLS-HUB: HUB FOR AI AGENTS
Open platform for discovering and comparing Agent Skills, tools, and MCP servers with ratings, trends, and auto-sync with GitHub.
★ 501 · TypeScriptSECURITY FOR AI CODERS - CAPS
Prismor blocks dangerous commands, secret leaks, and prompt injections in Claude Code, Cursor, and Windsurf in real time.
★ 494 · Python3000+ Bug Bounty Programs
Catalog of active bug bounty and VDP programs with MCP and API. Everything security researchers need.
★ 480 · TypeScriptSPONSIO - AI AGENT SECURITY
Sponsio offers deterministic security solutions for probabilistic AI agents, minimizing risks of unpredictable behavior.
★ 472 · PythonAGENTHOUND AGENT HUNT
Offensive security framework for AI agent infrastructure: reconnaissance, credential looting, model exfiltration, poisoning, and attack‑path analysis.
★ 464 · GoAI SOC: Security
Automated SOC based on security.
★ 456 · PythonASQAV-SDK - TRUST FOR AI AGENTS
Python/TypeScript SDK for signed action receipts of AI agents, policy control, and auditing. Works with LangChain, CrewAI, and MCP.
★ 449 · PythonLLMVault: OWASP LLM Training
Learn to protect AI systems: practical Prompt Injection, RAG, and agent vulnerabilities in one open training framework.
★ 356 · PythonGREYWALL — SAFELY ISOLATE AI AGENTS
Container‑free sandbox with deny‑by‑default: FS, network, and syscall isolation at the kernel level for Linux/macOS.
★ 315 · GoTAPESTRY: COMMON AI FOR NATIONS
The Tapestry project unites countries in a consortium to create a shared frontier model, from which each nation will derive its own sovereign AI system.
★ 305 · PythonSECURITYCLAW AUTONOMOUS SOC AGENT
Modular SOC agent on Python, monitors OpenSearch/Elasticsearch, builds RAG memory and validates anomalies with LLMs.
★ 280 · PythonAGENT-AUDIT SECURITY SCANNER
Static security scanner for LLM agents. Detects prompt injection, audits MCP configs, and performs taint analysis. Includes 51 rules mapped to OWASP Agentic Top 10 (2026)
★ 245 · PythonMINIMAL BOX FOR AGENTS
Run the AI agent in an isolated Minimal box on your PC. Build and execute code without risk to the system.
★ 240 · RustRED-TEAMING AI AGENTS IN PYTHON
Humanbound — adversarial testing engine, SDK, and CLI for AI agents. Runs locally or via Humanbound Platform. 218 stars on GitHub.
★ 239 · PythonCLAUDE CODE OWASP SECURITY 2025
Claude Code skill for adhering to OWASP best practices 2025‑2026: Top 10, ASVS 5.0, agentic AI security, and 20+ language nuances.
★ 233GUARDANA AI MODEL PROTECTION
Guardana scans model artifacts, live endpoints, MCP servers, and agent traces for security threats. It generates reproducible evidence for release decisions.
★ 225 · PythonGate Private Data Boundary
Gate creates a deterministic barrier between your data and AI, ensuring privacy without losing utility.
★ 214 · RustARGUS: AI AGENT SECURITY RED-TEAM TESTING
Open-source framework for red-team testing AI agents. 261 probes mapped to OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF. Browser, MCP, and mock payment support included
★ 210 · PythonRELIABLE AI AGENT ON PYTHON
Protect personal data with local request scrubbing via a local LLM before sending to the cloud.
★ 205 · PythonCLOSURE — CI GATING AGENT
Clausua — Rust-CLI agent guaranteeing deterministic completion of CI pipelines through precise gating.
★ 205 · RustADRIAN: AI AGENT SECURITY
Adrian monitors and blocks dangerous AI agent actions in real time, preventing malicious tool calls and prompt injections.
★ 203 · PythonDEFENSE MEMORY AI-AGENTS
Provides runtime defense against memory AI-agent poisoning (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
★ 203 · PythonNODE9-PROXY: SHIELD FOR AI AGENTS
node9-proxy provides deterministic management and auditing of autonomous AI agents, ensuring safe code execution.
★ 201 · TypeScriptMCP OBSERVATORY - PROTECTION ON CREST
CI-native security testing for MCP servers: attack simulation, schema deviation detection, and health assessment before agent launch.
★ 121 · TypeScriptSecure LLM for Code
An LLM-based system that analyzes AI-generated code for vulnerabilities and suggests automatic fixes. Integrated into CI/CD for continuous application protection.
★ 57 · PythonNew projects on this topic in Telegram
Telegram →