Security

A framework that has two AI models argue over a piece of code, with a third cross-validating, so a security or correctness finding survives adversarial attack instead of resting on one model's opinion.

• Code quality
• Security

A command-line toolkit for security-testing Retrieval Augmented Generation pipelines, covering 27 techniques across six kill-chain phases mapped to MITRE ATLAS, from detecting a RAG pipeline to exfiltrating or poisoning its knowledge base.

• Security

A self-hosted proxy that sits between an application and any LLM provider, redacting personal data and secrets and blocking prompt-injection attempts before a request reaches the model.

• LLM gateways
• Security

An open wire specification letting a separate Guardian Agent inspect what an AI coding agent is about to do and permit, deny or modify that action before it happens over an authenticated channel, with an audit trail that can be reconstructed afterward.

• Agent frameworks
• Security

A command-line security scanner for web applications that combines static analysis, dynamic testing against a running app, and LLM-based code review in one scan, aimed at developers who are not security specialists.

• Security

A desktop-native offensive security platform, built on Rust and Tauri, that combines Burp Suite-class web testing tooling with an autonomous AI agent driving the tools through a native MCP interface.

• Security

A defense-in-depth security toolkit for LLM agents that tracks where every piece of text came from, scans it for prompt injection, applies policy before a tool runs, and scrubs outbound secrets.

• AI evals
• Security

An open source security layer for AI agents that enforces role-based access control, requires human approval for high-risk actions, and writes a cryptographically signed, tamper-evident audit log.

• AI evals
• Security

A collection of security-focused skills for AI coding assistants such as Claude Code, Cursor and Copilot, from Red Hat's product security team, encoding security recommendations and practices as structured Markdown files an assistant reads while writing, testing or auditing code.

• Agent skills
• Security

An in-process agentic memory system for cyber threat intelligence that extracts CVEs, threat actors and indicators from analyst notes into a STIX knowledge graph and serves past cases back through MCP.

• Agent memory
• Security

A benchmark that measures whether a local coding agent keeps fixing a bug when repository content, such as a README, an issue or a code comment, tries to redirect it with a hidden instruction.

• AI evals
• Security

An open-source authorization engine for AI agents that checks every proposed action against policy before it runs, adding prompt-injection detection and confidence-based human review.

• AI evals
• Security

A fail-closed execution firewall that sits between AI coding agents and the system, allowing, denying or escalating each action and writing a signed, offline-verifiable receipt of the decision.

• AI evals
• Security

A self-hosted OSINT investigation platform that turns uploaded documents into an entity graph, then runs an autonomous agent that pivots on open-web infrastructure to extend the investigation.

• Security

An autonomous penetration-testing platform where an LLM agent plans and runs reconnaissance, active testing and vulnerability verification against an authorized target, then writes a report.

• Security

A deterministic transformer-shaped virtual machine that compiles a small assembly language into a runtime, executes it with no randomness, and proves the resulting computation with a transparent STARK proof system.

• Security
• Languages

An MCP server that connects Claude Code to the BountyLens bug-bounty hunt tracker, pushing findings, leads, tested endpoints and report drafts from the terminal to a web dashboard in real time.

• MCP servers
• Security

An MCP toolset that lets an AI agent operate Kali Linux penetration-testing tools, such as Nmap, sqlmap, Metasploit, Aircrack-ng and John the Ripper, through natural-language requests.

• MCP servers
• Security

An autonomous AI command center for penetration testing and security research that runs recursive tool-calling loops against a target with real-time streaming output, a local memory store and a choice of LLM backends.

• Security

A reverse proxy for LLM APIs that detects personal data in outgoing requests, replaces it with deterministic tokens before it reaches the model provider, and restores the original values in the response.

• LLM gateways
• Security

An autonomous agent harness for Kubernetes and GKE that continuously audits a fleet for compliance and security drift, opens pull requests with fixes through GitOps, and answers operational questions over chat.

• Security
• Containers

A command-line tool that runs SAST scans or reads existing scan reports from tools such as Checkmarx, CodeQL, Fortify or Snyk, then produces automatic code fixes for the vulnerabilities it can remediate.

• Code quality
• Security

An open-source AI assistant for exploring the MITRE ATLAS knowledge base of adversarial machine-learning tactics, techniques and mitigations, through natural-language questions, an MCP server, or direct customization.

• Security

A curated list of open-source tools and frameworks for securing autonomous AI agents, organized by security lifecycle stage from red teaming through runtime protection to governance.

• Security
• Curated lists