Red Team: open-source projects on GitHub
23 repositories on Red Team, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
CL4R1T4S - Hidden AI Info
Gather all system prompts from ChatGPT, Claude and other AI. Transparency and full control!
★ 53,197OPEN 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 · PythonREDAMON: AI PENTEST FRAMEWORK
Open‑source AI pentest framework: builds attack surface graph, autonomously exploits it in Kali sandbox with human approval and creates PR with fixes. MCP integration: co
★ 3,400 · PythonAI-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 · TypeScriptAI 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 · ShellCAIN-AGENT AI Pentest Agent
A real AI engineer for authorized penetration testing. Supports AWS, Azure, GCP, Aliyun, Tencent, and Huawei via a built‑in cloud module.
★ 952 · PythonClaude-BugHunter - Bug Hunt
51 skills, 15 slash commands and 574+ report templates for bug hunting and red-team work.
★ 786 · PythonAGENT OPFOR ATTACK EMULATION
Open‑source framework for simulating attacks on AI agents and MCP servers. Written in TypeScript and already has 377⭐.
★ 586 · TypeScriptBLITZ STRIKE PENTEST TOOLKIT
⚡ Blitz Strike — universal pentest toolkit for MCP. Methodology: reconnaissance, attack‑surface mapping, source‑to‑sink analysis, live validation. 57 escalation chains, 1
★ 518 · TypeScriptAI-Powered Pentest Tool
An offensive-security MCP server featuring 205 tools, 17 agents, and 60 probes for OWASP Top 10.
★ 514 · PythonPENTEST HARNESS FOR HACKERS
Pentest Harness — a self‑hosted AI‑agent framework for authorized pentests, bug bounty, security labs, and CTFs. Connect your own model via API; all sessions run strictly
★ 471 · TypeScriptAGENTHOUND AGENT HUNT
Offensive security framework for AI agent infrastructure: reconnaissance, credential looting, model exfiltration, poisoning, and attack‑path analysis.
★ 464 · GoAI REDTEAM AGENTS PLATFORM
AI red‑team platform: autonomous LLM agents perform a full pentest in an isolated Kali container and generate a report. LangGraph plan/act engine, models via LiteLLM, out
★ 409 · PythonLLMVault: OWASP LLM Training
Learn to protect AI systems: practical Prompt Injection, RAG, and agent vulnerabilities in one open training framework.
★ 356 · PythonRED-RUN: OFFENSIVE TOOLKIT CLAUDE
Red-run is a red team toolkit for Claude Code. Automates recon, exploits, and post-exploitation via AI agent. 296 stars on GitHub.
★ 308 · PythonCYBERSTRIKE: AI PENTEST AGENT
CyberStrike — an AI agent with 7300+ skills for autonomous pentesting (MITRE ATT&CK, CIS, OWASP, NIST), featuring lazy‑loading and zero context pollution.
★ 294 · TypeScriptAutoRedTeam-Orchestrator - AUTOMATE PENTESTS WITH AI
Modular platform for authorized testing and self-audit of the attack surface via MCP, generating SARIF for GitHub Code Scanning.
★ 269 · PythonAGENTPOISON: POISONING LLM AGENTS
The official NeurIPS 2024 implementation shows how to inject backdoors into the memory or knowledge base of LLM agents to test their robustness against attacks.
★ 256 · PythonAdvanced Post-Exploitation Framework
TypeScript-based post-exploitation framework for Red Team operations with modular payloads and C2 capabilities.
★ 255 · TypeScriptPERSONALIZED AI AGENT
code-abyss gives AI coders a unique personality through customizable personas, styles, and skills for Claude, Codex, Gemini, and OpenClaw.
★ 222 · JavaScriptWATCHTOWER: AI PENTEST AUTOMATION
Watchtower is a CLI tool using Python that uses LLM and LangGraph to automate pentest testing of websites locally for assessment. It creates workflows and generates vulne
★ 222 · PythonWRAITH Browser Hooking
WRAITH — a modern browser hooking framework, successor to BeEF and blind-XSS, for red teams, researchers, and educators. Used only for authorized testing, research, and t
★ 206 · JavaScriptArachneC2: P2P C2 framework
ArachneC2 is a decentralized libp2p-based bot control system, ensuring secure communication and flexible extensibility via modules. It supports AI traffic analysis for an
★ 77 · GoNew projects on this topic in Telegram
Telegram →