
pentestagent
AI agent framework for black-box security testing with autonomous multi-agent orchestration, built-in pentesting tools, and MCP integration for bug…

AI agent framework for black-box security testing with autonomous multi-agent orchestration, built-in pentesting tools, and MCP integration for bug…

Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.

AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions & skills before you clone — plus an…

AI-powered penetration testing assistant for automating recon, note-taking, and vulnerability analysis.

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual…

AI-powered Docker security scanner that explains vulnerabilities in plain English. An OWASP Lab Project.

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral…

An Open-Source Package for Textual Adversarial Attack.

Fully automatic censorship removal for language models

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

AI-native code security auditor on AgentField that proves exploitability with verdicts, traces, and actionable evidence.

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Gemini, Kimi, and more) through a QA…

WASM sandbox with capability enforcement for AI agent code. Agents can only call explicitly provided tools with defined constraints. Sandboxed…

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents