Unmask the hidden before the world does.
An autonomous AI framework that chains reconnaissance, exploitation, and post-exploitation into a single pipeline, then goes further by triaging every finding, implementing code fixes, and opening pull requests on your repository. From first packet to merged patch, no human intervention required.
LEGAL DISCLAIMER: This tool is intended for authorized security testing, educational purposes, and research only. Never use this system to scan, probe, or attack any system you do not own or have explicit written permission to test. Unauthorized access is illegal and punishable by law. By using this tool, you accept full responsibility for your actions. Read Full Disclaimer
Three AI agents attack simultaneously — one brute-forces SSH credentials with Hydra, one chains a CVE to escalate to root and defaces the homepage, one hunts down every XSS vulnerability on the frontend.
Reconnaissance ➜ Exploitation ➜ Post-Exploitation ➜ AI Triage ➜ CodeFix Agent ➜ GitHub PR
RedAmon doesn't stop at finding vulnerabilities, it fixes them. The pipeline starts with a 6-phase reconnaissance engine that maps your target's entire attack surface, then hands control to an autonomous AI agent that exploits CVEs, brute-forces credentials, and pivots through networks. Every finding is recorded in a Neo4j knowledge graph. When the offensive phase completes, CypherFix takes over: an AI triage agent correlates hundreds of findings, deduplicates them, and ranks them by exploitability. Then a CodeFix agent clones your repository, navigates the codebase with 11 code-aware tools, implements targeted fixes, and opens a GitHub pull request, ready for review and merge.
We maintain a public Project Board with upcoming features open for community contributions. Pick a task and submit a PR!
Want to contribute? See CONTRIBUTING.md for how to get started.
A special thanks to the people who go above and beyond — contributing code, spreading the word, and helping shape RedAmon into a better tool for the community. These are our project champions and evangelists. See CONTRIBUTING.md for how ranks work.
| Contributor | Rank | Tracks | GitHub |
|---|---|---|---|
| defektive | First Blood | Feature Builder | github.com/defektive |
| vishalsingh-arch | First Blood | Feature Builder | github.com/vishalsingh-arch |
Videos, writeups, and real-world experiences from security professionals using RedAmon in the field. Want to be featured? See the Content Creator track in CONTRIBUTING.md.
| Title | Link |
|---|---|
| RedAmon v2.2.0 — Phishing Social Engineering: From Payload to Root Shell in 2 Minutes | Watch |
| My AI Agent Exploited a CVE That Metasploit Couldn't — RedAmon Full Demo | Watch |
| RedAmon 2.0 — From 0 to 1000 GitHub Stars in 10 Days: Multi-Agent Parallel Attacks | Watch |
| Build an Autonomous AI Red Team Agent from Scratch — LangGraph + Metasploit + Neo4j Full Tutorial | Watch |
| Who | What | Link |
|---|---|---|
| Nipun Dinudaya | Deployed RedAmon on a company website — identified a critical SQL injection vulnerability that could have caused significant data exposure | Read on LinkedIn |
| Venkata Bhargav CH S | Used RedAmon during an internship at Ascent e-Digit Solutions — hands-on reconnaissance, DNS analysis, and attack surface mapping | Read on LinkedIn |
 Samuele Giampieri — Creator, Maintainer & AI Platform Architect AI Platform Architect & Full-Stack Lead with 15+ years of freelancing experience and more than 30 projects shipped to production, including enterprise-scale AI agentic systems. AWS-certified (DevOps Engineer, ML Specialty) and IBM-certified AI Engineer. Designs end-to-end ML solutions spanning deep learning, NLP, Computer Vision, and AI Agent systems with LangChain/LangGraph. LinkedIn · GitHub · Devergo Labs |
 Ritesh Gohil — Maintainer & Lead Security Researcher Cyber Security Engineer at Workday with over 7 years of experience in Web, API, Mobile, Network, and Cloud penetration testing. Published 11 CVEs in MITRE, with security acknowledgements from Google (4×) and Apple (6×). Secured 200+ web and mobile applications and contributed to Exploit Database, Google Hacking Database, and the AWS Community. Holds AWS Security Specialty, eWPTXv2, eCPPTv2, CRTP, and CEH certifications with expertise in red teaming, cloud security, CVE research, and security architecture review. LinkedIn · GitHub |
- Docker & Docker Compose v2+
That's it. No Node.js, Python, or security tools needed on your host.
| Resource | Without OpenVAS | With OpenVAS (full stack) |
|---|---|---|
| CPU | 2 cores | 4 cores |
| RAM | 4 GB | 8 GB (16 GB recommended) |
| Disk | 20 GB free | 50 GB free |
Without OpenVAS runs 6 containers: webapp, postgres, neo4j, agent, kali-sandbox, recon-orchestrator. With OpenVAS adds 4 more runtime containers (gvmd, ospd-openvas, gvm-postgres, gvm-redis) plus ~8 one-shot data-init containers for vulnerability feeds (~170K+ NVTs). First launch takes ~30 minutes for GVM feed synchronization. Dynamic recon and scan containers are spawned on-demand during operations and require additional resources.
git clone https://github.com/samugit83/redamon.git
cd redamonAfter starting the stack, open http://localhost:3000/settings (gear icon in the header) to configure everything. No .env file is needed — all configuration is done from the UI.
- LLM Providers — add API keys for OpenAI, Anthropic, OpenRouter, AWS Bedrock, or any OpenAI-compatible endpoint (Ollama, vLLM, Groq, etc.). Each provider can be tested before saving. The model selector in project settings dynamically fetches available models from configured providers.
- Tool API Keys — Tavily, Shodan, SerpAPI, and NVD keys to enable extended agent capabilities (web search, OSINT, CVE lookups).
- Tunneling — configure ngrok or chisel for reverse shell tunneling. Changes apply immediately without container restarts.
All settings are stored per-user in the database. See the AI Model Providers wiki page for detailed setup instructions.
Without GVM (lighter, faster startup):
docker compose --profile tools build # Build all images
docker compose up -d postgres neo4j recon-orchestrator kali-sandbox agent webapp # Start core services onlyComplete, With GVM:
docker compose --profile tools build # Build all images (recon + vuln-scanner + services)
docker compose up -d # Start all services (first GVM run takes ~30 min for feed sync)
# Total image size: ~15 GBGo to http://localhost:3000 — create a project, configure your target, and start scanning.
For a detailed walkthrough of every feature, check the Wiki.
Having issues? See the Troubleshooting guide or the Wiki Troubleshooting page.
docker compose ps # Check service status
docker compose logs -f # Follow all logs
docker compose logs -f webapp # Webapp (Next.js)
docker compose logs -f agent # AI agent orchestrator
docker compose logs -f recon-orchestrator # Recon orchestrator
docker compose logs -f kali-sandbox # MCP tool servers
docker compose logs -f gvmd # GVM vulnerability scanner daemon
docker compose logs -f neo4j # Neo4j graph database
docker compose logs -f postgres # PostgreSQL database
# Stop services without removing volumes (preserves all data, fast restart)
docker compose down
# Stop and remove locally built images (forces rebuild on next start)
docker compose --profile tools down --rmi local
# Full cleanup: remove all containers, images, and volumes (destroys all data!)
docker compose --profile tools down --rmi local --volumes --remove-orphansFor active development with Next.js fast refresh (no rebuild on every change):
Without GVM (lighter, faster startup):
docker compose -f docker-compose.yml -f docker-compose.dev.yml up -d postgres neo4j recon-orchestrator kali-sandbox agent webapp
Complete, With GVM:
docker compose -f docker-compose.yml -f docker-compose.dev.yml up -dBoth commands swap the production webapp image for a dev container with your source code volume-mounted. Every file save triggers instant hot-reload in the browser.
Refreshing Python services after code changes:
The Python services (agent, recon-orchestrator, kali-sandbox) already have their source code volume-mounted, so files are synced live. However, the running Python process won't pick up changes until you restart the container:
# Restart a single service (picks up code changes instantly)
docker compose restart agent # AI agent orchestrator
docker compose restart recon-orchestrator # Recon orchestrator
docker compose restart kali-sandbox # MCP tool serversNo rebuild needed — just restart.
For a complete development reference — hot-reload rules, common commands, important rules, and AI-assisted coding guidelines — see the Developer Guide.
If you need to update RedAmon to a new version, see Updating to a New Version.
- Full Wiki Documentation
- Overview
- Feature Highlights
- System Architecture
- Components
- Documentation
- Updating to a New Version
- Troubleshooting
- Legal
RedAmon is a modular, containerized penetration testing framework that chains automated reconnaissance, AI-driven exploitation, and graph-powered intelligence into a single, end-to-end offensive security pipeline. Every component runs inside Docker — no tools installed on your host — and communicates through well-defined APIs so each layer can evolve independently.
The platform is built around six pillars:
| Pillar | What it does |
|---|---|
| Reconnaissance Pipeline | Six sequential scanning phases that map your target's entire attack surface — starting from a domain or IP addresses / CIDR ranges — from subdomain discovery to vulnerability detection — and store the results as a rich, queryable graph. Complemented by standalone GVM network scanning and GitHub secret hunting modules. |
| AI Agent Orchestrator | A LangGraph-based autonomous agent that reasons about the graph, selects security tools via MCP, transitions through informational / exploitation / post-exploitation phases, and can be steered in real-time via chat. |
| Attack Surface Graph | A Neo4j knowledge graph with 17 node types and 20+ relationship types that serves as the single source of truth for every finding — and the primary data source the AI agent queries before every decision. |
| EvoGraph | A persistent, evolutionary attack chain graph in Neo4j that tracks every step, finding, decision, and failure across the attack lifecycle — bridging the recon graph and enabling cross-session intelligence accumulation. |
| CypherFix | Automated vulnerability remediation pipeline — an AI triage agent correlates and prioritizes findings from the graph, then a CodeFix agent clones the target repository, implements fixes using a ReAct loop with 11 code tools, and opens a GitHub pull request. |
| Project Settings Engine | 190+ per-project parameters — exposed through the webapp UI — that control every tool's behavior, from Naabu thread counts to Nuclei severity filters to agent approval gates. |
A fully automated, six-phase scanning engine running inside a Kali Linux container. Given a root domain, subdomain list, or IP/CIDR ranges, it maps the complete external attack surface: subdomain discovery (crt.sh, HackerTarget, Subfinder, Knockpy), DNS resolution, port scanning (Naabu), HTTP probing with technology fingerprinting (httpx + Wappalyzer), resource enumeration (Katana, GAU, Kiterunner), and vulnerability scanning (Nuclei with 9,000+ templates + DAST fuzzing). Results are stored as JSON and imported into the Neo4j graph.
GVM/OpenVAS performs deep network-level vulnerability assessment with 170,000+ NVTs — probing services at the protocol layer for misconfigurations, outdated software, default credentials, and known CVEs. Complements Nuclei's web-layer findings. Seven pre-configured scan profiles from quick host discovery (~2 min) to exhaustive deep scanning (~8 hours). Findings are stored as Vulnerability nodes in Neo4j alongside the recon graph.
A LangGraph-based autonomous agent implementing the ReAct pattern. It progresses through three phases — Informational (intelligence gathering, graph queries, Shodan, Google dorking), Exploitation (Metasploit, Hydra brute force, phishing/social engineering), and Post-Exploitation (enumeration, lateral movement). The agent executes 13 security tools via MCP servers inside a Kali sandbox, supports parallel tool execution via Wave Runner, and provides real-time chat interaction with guidance, stop/resume, and approval workflows. Deep Think mode enables structured strategic analysis before acting.
Supports 5 providers and 400+ models: OpenAI (GPT-5.2, GPT-5, GPT-4.1), Anthropic (Claude Opus 4.6, Sonnet 4.5), OpenRouter (300+ models), AWS Bedrock, and any OpenAI-compatible endpoint (Ollama, vLLM, LM Studio, Groq, etc.). Models are dynamically fetched — no hardcoded lists.
A Neo4j knowledge graph with 17 node types and 20+ relationship types — the single source of truth for the target's attack surface. The agent queries it before every decision via natural language → Cypher translation.
A persistent, evolutionary graph tracking everything the AI agent does — tool executions, discoveries, failures, and strategic decisions. Structured chain context replaces flat execution traces, improving agent efficiency by 25%+. Cross-session memory means the agent never starts from zero.
Launch multiple concurrent agent sessions against the same project. Each session creates its own AttackChain in EvoGraph. New sessions automatically load findings and failure lessons from all prior sessions, avoiding redundant work.
Unified view of active sessions — meterpreter, reverse/bind shells, and listeners. Built-in terminal with a Command Whisperer that translates plain English into shell commands.
Two-agent pipeline: a Triage Agent runs 9 hardcoded Cypher queries then uses an LLM to correlate, deduplicate, and prioritize findings. A CodeFix Agent clones the target repo, explores the codebase with 11 tools, implements fixes, and opens a GitHub PR — replicating Claude Code's agentic design.
An LLM-powered Intent Router classifies user requests into attack skills: CVE (MSF), Brute Force, Phishing, Denial of Service, or custom user-defined skills uploaded as Markdown files.
Scans GitHub repositories, gists, and commit history for exposed secrets using 40+ regex patterns and Shannon entropy analysis.
190+ configurable parameters across 14 tabs controlling every tool's behavior — from scan modules to agent approval gates. Managed through the webapp UI.
Upload a RoE document (PDF, TXT, MD, DOCX) to auto-configure project settings and enforce engagement constraints. Enforcement at both the recon pipeline (excluded hosts, rate limits, time windows) and AI agent (prompt injection, severity phase cap, tool restrictions) layers.
30+ interactive charts across 4 sections — attack chains & exploits, attack surface, vulnerabilities & CVE intelligence, and graph overview. All data pulled live from Neo4j and PostgreSQL.
LLM-based guardrail preventing targeting of unauthorized domains — blocks government sites, major tech companies, financial institutions, and social media platforms. Operates at both project creation and agent initialization.
Professional, client-ready HTML reports with 11 sections. When an AI model is configured, 6 sections receive LLM-generated narratives including executive summary, risk analysis, and prioritized remediation triage. View example report.
Full project backup and restore through the web interface — settings, conversations, graph data, recon/GVM/GitHub hunt results as a portable ZIP archive.
flowchart TB
subgraph User["👤 User Layer"]
Browser[Web Browser]
CLI[Terminal/CLI]
end
subgraph Frontend["🖥️ Frontend Layer"]
Webapp[Next.js Webapp<br/>:3000]
end
subgraph Backend["⚙️ Backend Layer"]
Agent[AI Agent Orchestrator<br/>FastAPI + LangGraph<br/>:8090]
ReconOrch[Recon Orchestrator<br/>FastAPI + Docker SDK<br/>:8010]
end
subgraph Tools["🔧 MCP Tools Layer"]
NetworkRecon[Network Recon Server<br/>Curl + Naabu<br/>:8000]
Nuclei[Nuclei Server<br/>:8002]
Metasploit[Metasploit Server<br/>:8003]
Nmap[Nmap Server<br/>:8004]
end
subgraph Scanning["🔍 Scanning Layer"]
Recon[Recon Pipeline<br/>Docker Container]
GVM[GVM/OpenVAS Scanner<br/>Network Vuln Assessment]
GHHunt[GitHub Secret Hunter<br/>Credential Scanning]
end
subgraph Data["💾 Data Layer"]
Neo4j[(Neo4j Graph DB<br/>:7474/:7687)]
Postgres[(PostgreSQL<br/>Project Settings<br/>:5432)]
end
subgraph LLMProviders["🧠 LLM Providers"]
OpenAI[OpenAI]
Anthropic[Anthropic]
LocalLLM[Local Models<br/>Ollama · vLLM · LM Studio]
OpenRouter[OpenRouter<br/>300+ Models]
Bedrock[AWS Bedrock]
end
subgraph External["🌐 External APIs"]
GitHubAPI[GitHub API<br/>Repos & Code Search]
end
subgraph Targets["🎯 Target Layer"]
Target[Target Systems]
GuineaPigs[Guinea Pigs<br/>Test VMs]
end
Browser --> Webapp
CLI --> Recon
Webapp <-->|WebSocket| Agent
Webapp -->|REST + SSE| ReconOrch
Webapp --> Neo4j
Webapp --> Postgres
ReconOrch -->|Docker SDK| Recon
ReconOrch -->|Docker SDK| GVM
ReconOrch -->|Docker SDK| GHHunt
Recon -->|Fetch Settings| Webapp
GHHunt -->|GitHub API| GitHubAPI
Agent -->|API| OpenAI
Agent -->|API| Anthropic
Agent -->|API| LocalLLM
Agent -->|API| OpenRouter
Agent -->|API| Bedrock
Agent --> Neo4j
Agent -->|MCP Protocol| NetworkRecon
Agent -->|MCP Protocol| Nuclei
Agent -->|MCP Protocol| Metasploit
Agent -->|MCP Protocol| Nmap
Recon --> Neo4j
GVM -->|Reads Recon Output| Recon
GVM --> Neo4j
GVM --> Target
GVM --> GuineaPigs
NetworkRecon --> Target
Nuclei --> Target
Metasploit --> Target
Nmap --> Target
NetworkRecon --> GuineaPigs
Nuclei --> GuineaPigs
Metasploit --> GuineaPigs
Nmap --> GuineaPigs
Full architecture diagrams (data flow, Docker containers, recon pipeline, agent workflow, MCP integration): ARCHITECTURE.md
Technology stack (70+ technologies across frontend, backend, AI, databases, security tools): TECH_STACK.md
| Component | Description | Documentation |
|---|---|---|
| Reconnaissance Pipeline | 6-phase automated OSINT and vulnerability scanning | README.RECON.md |
| Recon Orchestrator | Container lifecycle management via Docker SDK | README.RECON_ORCHESTRATOR.md |
| Graph Database | Neo4j attack surface mapping with multi-tenant support | README.GRAPH_DB.md · GRAPH.SCHEMA.md |
| MCP Tool Servers | Security tools via Model Context Protocol (Kali sandbox) | README.MCP.md |
| AI Agent Orchestrator | LangGraph-based autonomous agent with ReAct pattern | README.PENTEST_AGENT.md |
| CypherFix Agents | Automated triage + code fix + GitHub PR | README.CYPHERFIX_AGENTS.md |
| Web Application | Next.js dashboard for visualization and AI interaction | README.WEBAPP.md |
| GVM Scanner | Greenbone/OpenVAS network vulnerability scanner (170K+ NVTs) | README.GVM.md |
| PostgreSQL Database | Project settings, user accounts, configuration data | README.POSTGRES.md |
| Test Environments | Intentionally vulnerable Docker containers for safe testing | README.GPIGS.md |
| Resource | Link |
|---|---|
| Full Wiki (user guide) | github.com/samugit83/redamon/wiki |
| Developer Guide | readmes/README.DEV.md |
| Architecture Diagrams | readmes/ARCHITECTURE.md |
| Technology Stack | readmes/TECH_STACK.md |
| Troubleshooting | readmes/TROUBLESHOOTING.md |
| Changelog | CHANGELOG.md |
| Full Disclaimer | DISCLAIMER.md |
| License | LICENSE |
When updating RedAmon, all Docker images and volumes are rebuilt from scratch. Follow these steps to preserve your data.
Warning: Step 4 removes all database volumes. Any data not exported will be permanently lost.
1. Export all projects — go to each project's Settings and click Export to download backup ZIPs.
2. Stop all containers:
docker compose down3. Pull the latest version:
git pull origin master4. Remove old images, containers, and volumes:
docker compose down --rmi all --volumes5. Rebuild everything:
docker compose build --no-cache
docker compose --profile tools build --no-cache6. Start the new version:
# Full stack (with GVM):
docker compose up -d
# Core services only (without GVM):
docker compose up -d postgres neo4j recon-orchestrator kali-sandbox agent webapp7. Import your projects — open http://localhost:3000, create/select a user, and import each ZIP.
RedAmon is fully Dockerized and runs on any OS with Docker Compose v2+. For OS-specific fixes (Linux, Windows, macOS), see Troubleshooting Guide or the Wiki.
Contributions are welcome! Please read CONTRIBUTING.md for guidelines on how to get started, code style conventions, and the pull request process.
Samuele Giampieri — creator, maintainer & AI platform architect · LinkedIn · GitHub · Devergo Labs
Ritesh Gohil — maintainer & lead security researcher · LinkedIn · GitHub
For questions, feedback, or collaboration inquiries: devergo.sam@gmail.com
This project is released under the MIT License.
See DISCLAIMER.md for full terms of use, acceptable use policy, and legal compliance requirements.
Use responsibly. Test ethically. Defend better.