Skip to main content

​
What is RAPTOR?

RAPTOR is an autonomous offensive/defensive security research framework built on Claude Code. It empowers security research with agentic workflows and automation. RAPTOR stands for Recursive Autonomous Penetration Testing and Observation Robot. (We really wanted to name it RAPTOR)

​
Key capabilities

RAPTOR autonomously:
  1. Scans your code with Semgrep and CodeQL and tries dataflow validation
  2. Fuzzes your binaries with American Fuzzy Lop (AFL)
  3. Analyses vulnerabilities using advanced LLM reasoning
  4. Exploits by generating proof-of-concepts
  5. Patches with code to fix vulnerabilities
  6. FFmpeg-specific patching for Google’s recent disclosure
  7. OSS Forensics for evidence-backed GitHub repository investigations
  8. Agentic Skills Engine for security research & operations (SecOpsAgentKit)
  9. Offensive Security Testing via autonomous specialist agent with SecOpsAgentKit
  10. Cost Management with budget enforcement, real-time tracking, and quota detection
  11. Reports everything in structured formats
RAPTOR combines traditional security tools with agentic automation and analysis, deeply understands your code, proves exploitability, and proposes patches.

​
What makes RAPTOR unique?

Beyond RAPTOR’s potential for autonomous security research and community collaboration, it demonstrates how Claude Code can be adapted for any purpose with RAPTOR packages.

​
Recent improvements

  • LiteLLM Integration: Unified LLM interface with Pydantic validation, smart model selection, and cost tracking
  • SecOpsAgentKit: Offensive security specialist agent with comprehensive penetration testing capabilities
  • Cost Management: Budget enforcement, real-time callbacks, and intelligent quota detection
  • Enhanced Reliability: Multiple bug fixes improving robustness across CodeQL, static analysis, and LLM providers

​
OSS Forensics Investigation

RAPTOR includes comprehensive GitHub forensics capabilities via the /oss-forensics command:
  • Evidence Collection: Multi-source evidence gathering (GH Archive, GitHub API, Wayback Machine, local git)
  • BigQuery Integration: Query immutable GitHub event data via GH Archive
  • Deleted Content Recovery: Recover deleted commits, issues, and repository content
  • IOC Extraction: Automated extraction of indicators of compromise from vendor reports
  • Evidence Verification: Rigorous evidence validation against original sources
  • Hypothesis Formation: AI-powered evidence-backed hypothesis generation with iterative refinement
  • Forensic Reporting: Detailed reports with timeline, attribution, and IOCs

​
Offensive Security Agent

RAPTOR includes an autonomous offensive security specialist agent with specialized skills from SecOpsAgentKit:
  • Web application security testing (SQLi, XSS, CSRF, auth bypass)
  • Network penetration testing and enumeration
  • Binary exploitation and reverse engineering
  • Fuzzing and vulnerability discovery
  • Exploit development and PoC generation
  • Security code review with adversarial mindset
Safe operations auto-execute; dangerous operations require explicit user confirmation.

​
Architecture overview

RAPTOR is a multi-layered system with progressive disclosure:

​
Claude Code Decision System

  • Bootstrap (CLAUDE.md) → Always loaded
  • Tier1 (adversarial thinking, analysis-guidance, recovery) → Auto-loads when relevant
  • Tier2 (9 expert personas) → Load on explicit request
  • Agents (offsec-specialist) → Autonomous offensive security operations
  • Alpha (custom skills) → User-created

​
Python Execution Layer

  • raptor.py → Unified launcher
  • packages/ → 9 security capabilities
  • core/ → Shared utilities
  • engine/ → Rules and queries

​
Key features

  • Adversarial thinking: Prioritizes findings by Impact × Exploitability / Detection Time
  • Decision templates: 5 options after each scan
  • Progressive disclosure: 360t → 925t → up to 2,500t with personas
  • Dual interface: Claude Code (interactive) or Python CLI (scripting)
Alpha status disclaimer: RAPTOR was hacked together in free time, held together by vibe coding and duct tape. Consider it an early release.What will make RAPTOR truly transformative is community contributions. It’s open source, modular, and extensible.
Automatic installation: Unless you use the devcontainer, RAPTOR will automatically install tools without asking. Check DEPENDENCIES.md first.

​
Authors

Gadi Evron, Daniel Cuthbert, Thomas Dullien (Halvar Flake), Michael Bargury & John Cartwright (@gadievron, @danielcuthbert, @thomasdullien, @mbrg & @grokjc)

​
License

MIT License - Copyright (c) 2025 Gadi Evron, Daniel Cuthbert, Thomas Dullien (Halvar Flake), and Michael Bargury Make sure to review the licenses for the various tools. For example, CodeQL does not allow commercial use.

​
Next steps

Quick start

Get up and running with RAPTOR in minutes

Installation

Detailed installation instructions and setup

Architecture

Learn about RAPTOR’s technical architecture

Commands

Explore available commands and capabilities

Build docs developers (and LLMs) love

Get started for freeTalk to us