redamon

Unmask the hidden before the world does

RedAmon is an open-source, self-hosted AI penetration testing framework that maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens pull requests that fix what it finds. From first packet to merged patch, with human oversight at every critical step.

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

🏆 Flagship result: RedAmon solves 101 / 104 (97.1%) of the XBOW web-security benchmark fully black-box. Every solve ships a complete, unedited raw agent session and a reproducible, step-by-step walkthrough: open any row and read exactly how the flag fell, tool call by tool call. Auditable, line by line. See the XBOW Validation Benchmark scorecard.

📊 Coverage, measured and self-scored: the Bug Bounty Coverage — The Full Taxonomy Audit (PDF, 124 pages) audits RedAmon against all 397 classes of web bug-bounty finding, one line at a time, naming the exact module, skill or scanner behind every verdict, and scoring the recon pipeline and the agentic system separately against their own remit. It is deliberately self-critical, it records what is missing as plainly as what is covered: 134 classes complete, 210 in the build backlog, 44 deliberately excluded, with one explicit decision for every class.

RedAmon launches multiple reconnaissance tools in parallel, each feeding results into a shared knowledge graph in real time. Tools spin up, adapt their scope based on live discoveries, and coordinate without manual intervention. The entire attack surface -- subdomains, ports, endpoints, parameters -- materializes in minutes, not hours.

Industry-standard scanners chained so each tool's output feeds the next, then merged into a single Neo4j knowledge graph. Findings are deduplicated, relationships are explicit, and the agent inherits a structured, fully connected attack surface ready to query in natural language.

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 validates CVE exploitability, tests credential policies, and maps lateral movement paths. 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.

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 From the same creator: Pathbreak - Agentic Cloud Security See the attack path. Then break it. Pathbreak is an agentic cloud security platform that discovers and validates the real attack paths a threat actor would exploit across your cloud. It catches the control-plane chains most tools miss. Pathbreak - agentic cloud security pathbreak.io

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

Anthropic Cyber Verification Program: the team behind RedAmon is approved under Anthropic's Cyber Verification Program.

• Docker Engine 28.0.0 or newer & Docker Compose v2+ (check with docker version --format '{{.Server.Version}}')
  • macOS: Docker Desktop, with Memory raised to at least 4 GB (8 GB with --gvm) in Settings → Resources. Clone under ~/ so the path is inside the default File Sharing list.
  • Windows: Docker Desktop with the WSL2 backend, run from inside the WSL2 filesystem (~/), not /mnt/c/.

That's it. No Node.js, Python, or security tools needed on your host.

RAM is checked at start. ./redamon.sh refuses to start when the memory Docker can use does not cover the minimum of every service the profile runs (the memory allocator's per-service floors, see README.MEMORY_GOVERNOR.md). With the default reserves that is about 6.5 GB for the core stack and about 9.6 GB with OpenVAS. REDAMON_SKIP_RAM_GATE=1 skips the check.

Without OpenVAS runs 9 containers: webapp, postgres, neo4j, agent, kali-sandbox, recon-orchestrator, docker-broker (a filtering Docker-socket proxy that the recon orchestrator's spawned scan containers go through, so they can only launch the known tool images), and the plugin platform's plugin-runner and plugin-gateway. 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.

Disk sizing for a real deployment. The figures above are bare minimums to build and run the stack (fixed platform footprint: ~70 GB without OpenVAS, ~95 GB with - measured by true on-disk image size after deduplicating the shared Kali base layers). For an always-on server running real engagements, add ~100 GB of free space for operational data - the Neo4j attack graph, scan artifacts/outputs, Postgres, and container logs all grow with use. That means 200 GB without OpenVAS, 250 GB with OpenVAS, each leaving well over 100 GB free for operations. See the deployment guide for the full breakdown.

git clone https://github.com/samugit83/redamon.git
cd redamon

# Without GVM (lighter, faster startup):
./redamon.sh install

# With GVM / OpenVAS (full stack, ~30 min first run):
./redamon.sh install --gvm

The script builds all images and starts the services.

At the end of the install (and on every ./redamon.sh up or ./redamon.sh update if no admin exists), you will be prompted in the terminal:

[WARN] No admin user found. Let's create one.

  Admin name: Your Name
  Admin email: [email protected]
  Admin password: ********
  Confirm password: ********

• Admin name -- display name shown in the UI (e.g. Admin, your name, anything you want).
• Admin email -- used to log in at http://localhost:3000/login.
• Admin password -- minimum 12 characters.

After creation, open http://localhost:3000 and sign in with the email and password you just set.

No prompt appeared? On a heavy first boot (especially --gvm, or a small VM) the webapp can take a while to come up, so the automatic prompt may be skipped. Create the admin at any time with:

./redamon.sh create-admin

It waits for the webapp, then prompts for the same details. It is safe to re-run: reusing an existing admin's email resets that password, a new email adds another admin.

What the admin can do:

• Switch between all users via the user dropdown in the header (including users without a password).
• Create new users (with or without a password) and assign them admin or standard roles.
• Set or change any user's password.
• Delete users (except themselves).
• Access the Users management page from the header navigation.

Standard users can only log in (if they have a password set by an admin), change their own password, and use the app within their own scope. They cannot switch users, create users, or access user management.

If you forget the admin password, reset it from the terminal:

./redamon.sh reset-password   # reset an EXISTING user's password
./redamon.sh create-admin     # create the first admin, or reset an admin by re-entering its email

Use create-admin when no admin exists yet (it upserts on email); reset-password only updates a user that already exists.

Open http://localhost:3000/settings (gear icon in the header) to configure everything. No .env file is needed.

• 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.
• API Keys -- Tavily, Shodan, SerpAPI, NVD, Vulners, URLScan, and threat intelligence keys (Censys, FOFA, OTX, Netlas, VirusTotal, ZoomEye, CriminalIP) to enable extended agent capabilities (web search, OSINT, CVE lookups, passive threat intel). Uncover multi-engine search keys (Quake, Hunter, PublicWWW, HunterHow, Google, Onyphe, Driftnet) expand target discovery across 13 search engines -- shared keys (Shodan, Censys, FOFA, etc.) are automatically reused. Supports key rotation -- configure multiple keys per tool with automatic round-robin rotation to avoid rate limits.
• 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.

Go to http://localhost:3000 -- create a project, configure your target, and start scanning.

For a detailed walkthrough of every feature, check the Wiki.

Prefer video? Watch the Product Demos playlist on YouTube for step-by-step tutorials.

Having issues? See the Troubleshooting guide or the Wiki Troubleshooting page.

All lifecycle management is handled by a single script:

Flags can be combined: ./redamon.sh install --gvm --kbase

Just run:

./redamon.sh update

The script pulls the latest code from GitHub, detects which Dockerfiles and source files changed, rebuilds only the affected images, and restarts the updated services. Your databases, scan results, and reports are preserved -- volumes are never deleted.

One-time note when a release adds a new background service. update re-execs the freshly-pulled script so new build/start rules apply automatically -- but only for the script version you are updating from. When updating from a version that predates this self-heal (i.e. your first update onto it), run ./redamon.sh up once right after update so any newly added core service is started:

./redamon.sh update && ./redamon.sh up

up is idempotent -- it starts only what is missing and leaves running containers untouched. After this one-time step, plain ./redamon.sh update handles everything on its own.

Upgrading across 6.9 (repository reorganization). 6.9 grouped the top-level directories under scanners/, services/, testing/, tooling/ and docs/. git pull moves only tracked files, so data that git does not track -- the knowledge-base index, past scan outputs, and the single-host deploy .env and TLS material -- would otherwise be left behind at the old paths. update (and up/status) migrate it for you automatically and print what moved. If any file was written by a container as root and could not be moved, finish it with:

sudo ./redamon.sh migrate-layout

The webapp also checks for updates automatically and shows a notification in the UI when a new version is available.

The Quick Start above runs RedAmon locally on localhost. To run a shared, internet-reachable instance on a Linux server (EC2, DigitalOcean, Hetzner, or bare metal), use the single-host deploy in tooling/deploy/single-host/. It drives redamon.sh over SSH from your laptop and wraps the stack in the internet-facing security layer RedAmon omits by default: nginx + TLS (Let's Encrypt), a host firewall, SSH hardening, and fail2ban, with a single public HTTPS origin so only the login page is reachable and everything else stays bound to loopback.

cd tooling/deploy/single-host
cp .env.example .env      # set HOST_IP, DOMAIN, SSH_KEY_PATH, OPERATOR_ALLOW_CIDRS,
                          # LETSENCRYPT_EMAIL, ADMIN_* ...
./deploy.sh init          # first build takes 30-60 min, then log in at https://<domain>/

Full walkthrough: Wiki: Deploying to a Server. Complete reference: tooling/deploy/single-host/README.md.

For contributors and active development with Next.js fast refresh:

./redamon.sh up dev           # auto-detects GVM mode from install

Tool images are built automatically on first run if they don't exist yet. The dev override swaps the production webapp image for a dev container with your source code volume-mounted. Every file save triggers instant hot-reload in the browser.

Rebuild a single service:

docker compose build <service>                    # Rebuild one image
docker compose up -d --no-deps <service>          # Restart only that service

Common dev commands:

docker compose ps                                 # Check service status
docker compose logs -f <service>                  # Follow logs for a service
docker compose down                               # Stop all (preserves volumes)
docker compose --profile tools down --rmi local   # Remove built images
docker compose --profile tools down --rmi local --volumes --remove-orphans  # Full cleanup

Reclaim disk space:

docker system df                                  # Show Docker disk usage (add -v for per-image breakdown)
docker image prune -f                             # Remove dangling images (auto-run by `./redamon.sh install` and `update`)
docker builder prune -f                           # Drop unused build cache (auto-run after every successful build; opt out with REDAMON_NO_AUTO_PRUNE=1)
docker builder prune -af                          # Drop ALL build cache, including what the current images reuse -- frees no extra disk and makes the next rebuild cold
docker container prune -f                         # Remove stopped containers

For a complete development reference -- hot-reload rules, common commands, important rules, and AI-assisted coding guidelines -- see the Developer Guide.

The agent's web_search tool includes a local Knowledge Base -- a RAG pipeline that searches curated security datasets (GTFOBins, LOLBAS, OWASP WSTG, NVD CVEs, ExploitDB, Nuclei templates, and agent skill docs) before falling back to Tavily web search. When the KB returns a high-confidence match, Tavily is skipped entirely for faster, offline-capable results.

How it works: When the KB is enabled, install / up / update builds a lightweight KB index (~1,200 chunks in 10-15 min on CPU). At query time, the agent runs a hybrid retrieval pipeline (FAISS vector search + Neo4j fulltext), reranks with a cross-encoder, and checks a confidence threshold. If the score is high enough, results come from the local KB. Otherwise, it falls back to Tavily or merges both.

Default behavior: The KB is opt-in. ./redamon.sh install produces a lightweight install (~4.4 GB lighter, Tavily-only web search). To enable the local KB, pass --kbase:

./redamon.sh install --kbase

On first install with --kbase, RedAmon detects your hardware (GPU / CPU / API) and offers a quick-start profile. The choice is persisted, so subsequent update / up commands respect it without re-passing the flag.

Speed up ingestion with API embeddings: By default, embeddings run locally on CPU/GPU. On CPU-only machines, large datasets (ExploitDB, NVD) can take hours. You can offload embedding to an external API by creating a .env file from the template:

cp .env.example .env

Then configure the embedding API in .env:

Example with Ollama (free, local, no API key cost):

KB_EMBEDDING_USE_API=true
KB_EMBEDDING_API_BASE_URL=http://host.docker.internal:11434/v1
KB_EMBEDDING_API_KEY=ollama
KB_EMBEDDING_API_MODEL=nomic-embed-text

Important: Ingestion and query must use the same model. If you switch models, rebuild the index: make -C services/knowledge_base kb-rebuild-lite MODE=docker

Manage the KB:

./redamon.sh kb build lite          # Build with lite profile (~30-60s with API)
./redamon.sh kb build standard      # Add NVD CVEs
./redamon.sh kb update nvd          # Incremental NVD refresh
./redamon.sh kb stats               # Show index statistics
./redamon.sh kb rebuild lite        # Wipe and rebuild from scratch

For full technical documentation -- query pipeline, data sources, ingestion profiles, scoring, security model -- see the Knowledge Base Technical Reference or the Wiki: Knowledge Base & Web Search.

• Full Wiki Documentation
• Overview
• Built for Enterprise, Secure by Design
• Security & Threat Model
• Feature Highlights
• System Architecture
• Components
• Documentation
• Troubleshooting
• RedAmon HackLab
• Community Showcase
• 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:

RedAmon is engineered to drop into a real security organization, not just a researcher's laptop.

• Secure by design, STRIDE threat-modeled. The whole platform is assessed end to end under STRIDE and hardened in independently verified waves: code-level privilege separation, a filtering Docker broker in front of the host socket, fail-closed auth, SSRF egress guards, secret redaction, append-only audit trails, and a non-disableable guardrail that blocks government, military, and intergovernmental targets. See the Security Posture and Threat Model.
• Fully isolated and containerized. Every tool, scanner, and agent runs in its own container with no host-level execution. Scan jobs are spawned as ephemeral sibling containers with their own filesystem and network namespace, then torn down on completion, keeping the host clean and containing the blast radius of any exploit.
• Governed and multi-tenant. Multi-user / multi-project tenancy with admin and standard roles, DB-level user_id + project_id scoping on every node, Rules-of-Engagement enforcement, human-in-the-loop approval gates, and hundreds of per-project settings give teams the control an enterprise engagement requires.

Deploy to a server in one command. Beyond local localhost, RedAmon ships a hardened single-host deploy that stands up a shared, internet-reachable instance and wraps the stack in nginx + TLS (Let's Encrypt), a host firewall, SSH hardening, and fail2ban, exposing a single public HTTPS origin:

cd tooling/deploy/single-host
cp .env.example .env      # set DOMAIN, HOST_IP, SSH_KEY_PATH, ADMIN_* ...
./deploy.sh init          # builds the full stack and brings it up over SSH

Full walkthrough: Wiki: Deploying to a Server.

RedAmon is offensive software, so we hold it to the standard it tests others by. It is engineered secure by design and has been assessed end to end under the STRIDE methodology (Spoofing, Tampering, Repudiation, Information disclosure, Denial of service, Elevation of privilege), with findings remediated in sequenced, independently verified waves.

This is not a marketing claim. It is grounded in a published, evidence-based analysis you can read:

• Security Posture - the full defense-in-depth control catalog: every layer implemented, mapped to the code.
• Threat Model - the assets, trust boundaries, data flows, entry points, and network surface the analysis was built on.

Highlights of what is implemented:

• Code-level privilege separation. The target-facing worker is the least trusted component and holds no secrets; a filtering docker-broker stands between the orchestrator and the host Docker socket (image allowlist, denies --privileged, host-root binds, dangerous capabilities).
• Two deployment postures, one trust model. Local (backends bound to loopback) and a hardened public-internet deploy that adds nginx + TLS, an operator gate, login rate-limiting, and a single public origin.
• Fail-closed by default. Unset auth tokens reject rather than serve, default database credentials are refused and rotated, WebSockets require a signed ticket plus a server-side same-origin check, and every request is scoped to its authenticated owner (per-user access control with anti-enumeration 404s).
• Defense in depth. SSRF egress guards, secret redaction in logs, append-only audit trails, container-escape hardening, decompression and concurrency caps, and supply-chain pinning (sha256 + commit pins).
• A non-disableable hard guardrail blocks government, military, and intergovernmental targets regardless of configuration.
• Third-party plugins are contained, not trusted. The plugin platform installs only from an Ed25519-signed catalog, runs each plugin under its own UID in a runner with no internet and no database or LLM credentials, reaches the stack only through a two-route proxy that re-authorizes every call, and lets a plugin change the agent's instructions only through text a person approves.
• Verified, release-gated remediation. Fixes ship in sequenced waves, each independently verified with live exploit reproduction before and after the patch. See the Changelog security entries.

Found a vulnerability? See our Security Policy for private disclosure.

A fully automated, end-to-end external attack-surface mapper running inside a Kali Linux container. Give it one input (a root domain, a subdomain list, IP/CIDR ranges, or a Domain batch: a list of hostnames grouped by domain and scanned one group after another into a single graph) and the pipeline returns a complete, structured picture of the target: every subdomain, every live host, every open port, every HTTP service with its technology stack, every crawled endpoint and discovered parameter, every CVE the target is likely vulnerable to, plus dedicated scanners for GraphQL APIs, subdomain takeovers, hidden virtual hosts behind reverse proxies, web cache poisoning & deception, and an Adversarial AI Surface layer that tags AI runtimes / vector DBs / LLM frontends / proxies / MCP servers / chat / completion / embedding / RAG endpoints and prompt-injectable parameters using header / favicon / title / path / parameter-name signatures, then actively confirms them with a dedicated AI Surface Recon module (benign chat-shape probes, MCP handshake + tool-poisoning scan, vector-DB reads — no LLM calls).

Everything runs on a fan-out / fan-in architecture: each phase fires as many tools in parallel as the work allows, then converges before the next phase begins. 40+ industry tools integrate into one coordinated workflow, wildcard DNS poisoning is filtered out automatically with puredns, and stealth mode keeps the entire pipeline running on passive sources only when active probing is off-limits. Findings stream into the Neo4j knowledge graph on a background thread so the scan never blocks on database writes, and the raw JSON is preserved for download. The detailed tool-by-tool breakdown is in the matrix below.

Wiki: Running Reconnaissance | Technical: README.RECON.md

_{*Amass can run in active mode when configured. Knockpy performs active DNS probing.}

Run any single tool from the pipeline independently without re-running the entire scan. Up to 12 partial recons can run in parallel per project, each with independent logs, stop controls, and status badges visible in both the Graph toolbar and Project Settings header. Each tool section has a play button that opens a modal where you can review existing graph data, add custom targets (subdomains, IPs, ports, or URLs), and launch the tool in isolation. Results are merged back into the Neo4j graph using MERGE operations -- duplicates are updated, not recreated. The tool runs with all project settings (timeouts, wordlists, API keys, proxy) applied automatically. All pipeline tools support partial recon.

Wiki: Recon Pipeline Workflow -- Partial Recon

Optional LLM-augmented decision points wired inside the recon pipeline where static look-ups historically drift -- Nuclei prunes its tag list to the detected tech stack, the WAF classifier catches header-stripped Cloudflare/AWS WAF/Imperva, and many others across FFuf, Nuclei false-positive filtering, and subdomain-takeover disambiguation. Each hook is a cascade fallback after the static path with a deterministic safe fallback, so an LLM outage cannot break a scan. One master toggle in the Target tab governs them all.

The recon pipeline uses TypeSafe Jev, a typed decision model, for nine decisions: what kind of page each URL is, which host Hakrawler crawls first, which directories and extensions FFuf fuzzes, whether a tool failed or just found nothing, which Nuclei tags to run, whether a WAF is in front, whether a takeover is real, and which serialization format a flagged blob is. Three more Jev hooks steer the Route Exposure Scan: which routes fill its request budget, whether a lead's page is a disguised login wall, and how sensitive each lead is, so the agent confirms the most sensitive first. They only rank and order: no lead is dropped, and without a Jev answer the scan is the deterministic one. Jev needs a token on the project owner's account; see how it works in the Jev Meets the Recon Pipeline walkthrough on redamon.org.

Wiki: TypeSafe Jev

Wiki: AI in Pipeline

Where the recon pipeline finds the AI surface, the AI Gauntlet attacks it. Pick the discovered LLM endpoints (or type a custom URL), choose a tool, confirm the Rules of Engagement, and launch: a short-lived container runs the target through four industry red-team tools -- garak (broad single-shot scanner, 40 probe families), PyRIT (bounded multi-turn jailbreaks), Giskard (LLM-assisted safety scan), and promptfoo (dataset red-team eval) -- measuring an Attack Success Rate per attack and writing the confirmed weaknesses back onto the graph as OWASP-LLM / MITRE-ATLAS-mapped Vulnerability findings with evidence transcripts.

It is deterministic (seeds, fixed bounds, pinned tool versions) and runs with zero external egress: every judge / grader / embedding call is forced to a local Ollama model, so no payload or transcript ever leaves your machine. Off by default and RoE-gated, with live phase-by-phase progress, and findings surfaced in the Red Zone AI Gauntlet Vulnerabilities table and the pentest report.

Wiki: AI Gauntlet | Technical: AI_GAUNTLET_TECH_DOC.md

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.

Wiki: GVM Vulnerability Scanning | Technical: README.GVM.md

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 credential testing, social engineering simulation), and Post-Exploitation (enumeration, lateral movement). The agent executes 22 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.

Wiki: AI Agent Guide | Technical: README.AGENTIC_SYSTEM.md

_{All MCP tools run inside a Kali Linux sandbox container. Workspace FS and Background Jobs tools run in-process inside the agent container and operate exclusively on the per-project workspace at /workspace/<projectId>/ -- path validation rejects every traversal trick (project-id injection, symlink escape, zip-slip, tar-slip). See Agent Workspace wiki page for the full reference. Tools marked as dangerous require manual confirmation before execution. Stealth mode restricts active tools to passive-only or single-target operations. Note: WPScan is licensed under the WPScan Public Source License (not MIT). Free for pentesting assessments and personal use; commercial use may require a separate license from wpscan.com.}

Beyond the 5 built-in MCP servers above, you can plug any Model-Context-Protocol server into the agent as a tool plugin (Shodan, GitHub, Censys, Hugging Face, mitmproxy, your own internal MCPs) without editing code, rebuilding containers, or running migrations. Open Global Settings → MCP Tool Plugins.

Two paths: pick one of the prefilled Quick-Add presets (OSINT, threat-intel, cloud, web-app scanners, reporting, reverse engineering; categories tagged on every card), or click Add MCP for a manual config. Three transports supported: stdio, sse, streamable_http. The orange Discover and add new tools button runs a live list_tools() against the draft, returns within 30 seconds, and auto-imports each discovered tool with its name, description, and a JSON-Schema-derived args_format (types, enums, defaults, min/max, per-property descriptions). Save → tools auto-appear in every project's Tool Matrix and in the agent's system prompt within ~1 second. No agent restart, no prisma db push.

Full operator manual (every form field, every preset, the auth flow, the live discovery workflow, validation rules, troubleshooting, and the storage / security model): MCP Tool Plugins wiki page.

The mirror image of the plugins above. Instead of RedAmon's agent reaching out to tools, your agent connects in and drives RedAmon: your Claude Code session, an internal triage assistant, a nightly CI job, anything that speaks the Model Context Protocol. Mint an access token in Global Settings → MCP Server and it gets 51 tools behind 18 permissions: list projects, read scan status and settings, query the attack-surface graph in plain English or raw Cypher, read findings / suppressed findings / remediations, see why a finding ranks where it does and read its evidence, submit a quoted evidence review (RedAmon recomputes the score; the agent never sets one), record a triage verdict, start or stop a Priority Board run (spaced and capped per project), mute and unmute findings behind their own opt-in permission, run saved graph views, compare saved scan versions, get an attack-surface overview, exploit paths and blast radius, start / stop / queue a recon run, open an engagement, manage recon presets, (off by default, behind three independent switches) run a command in the Kali sandbox, and (off by default) be the brain of a RedAmon chat with Agent in the Loop.

The token acts as you, inside your own projects. It is re-checked on every call, so a revoke takes effect on the agent's next call rather than its next reconnect; every graph read is rewritten to match only your tenant's nodes and runs in a read-only Neo4j session; and every write is a positive allowlist. Deliberately not exposed: the agent chat, deleting projects, your API keys, re-pointing a project's target, the engagement record, Mute Rules, setting a finding's score directly, changing a verdict a person made in the app, and any graph write beyond verdicts, reviews, triage runs and (opt-in) mutes. MCP_SERVER_ENABLED is off after a normal install and refused over plain HTTP on a server deploy, and MCP_DISABLED_TOOLS withdraws a single misbehaving tool without taking the whole surface down.

Connecting an agent tells it that the tools exist. It does not tell it what RedAmon is, what the recon pipeline produces, or which of the 51 tools to reach for first. Agent Onboarding writes those instructions for you. Pick one of 15 Agent Profiles (bug bounty, penetration testing, continuous attack-surface monitoring, vulnerability management, triage assistance, asset inventory / CMDB, compliance evidence, DevSecOps CI gating, reporting, M&A and third-party risk, threat-intel correlation, SOC enrichment, research and training, Agent in the Loop, or custom) and RedAmon ticks the permissions that job needs and generates a pack tailored to it: a SKILL.md plus reference files covering the operating model, the graph's shape, the tool sequence for that job, the traps specific to it, and tool by tool exactly what this token can and cannot do. The tool facts are read from the server's own live tool list at export time, so a pack can never describe a tool differently from how the server serves it. Clients that never load a skill file (Cursor, Windsurf, Cline, Goose, Gemini CLI) receive a shorter version of the same guidance inline the moment they connect.

No profile ever ticks kali:exec or recon:overwrite for you, not even the ones that recommend them: a shell on a target-facing box and an irreversible graph wipe should never arrive as the side effect of choosing an item from a dropdown.

Agent Skills teach RedAmon's agent. Agent Onboarding teaches yours.

Pick Agent in the Loop as a chat's model and every reasoning step of that run goes to your agent instead of a provider: Claude Code or Codex claims each step over the MCP server, writes the decision, and RedAmon runs it with its own tools, graph and gates. No provider key is needed, your agent's own subscription does the thinking, and every approval stays with you: phase changes, questions and dangerous tools are answered in the RedAmon drawer, never over MCP, and in such a run dangerous tools always ask. The token that drives it holds agent:loop and read permissions only. On by default with the MCP server (./redamon.sh writes both switches into .env); the onboarding pack for the Agent in the Loop profile ships the skill and the client settings for both clients.

Wiki: Agent in the Loop | Technical: README.MCP.SERVER.md §9

Wiki: MCP Server | Wiki: MCP API Reference | Technical: README.MCP.SERVER.md

Watch the demo: RedAmon Agent Workspace: AI Runs 4 Parallel Pentests and Writes Its Own Report (YouTube)

Every project gets a persistent /workspace/<projectId>/ directory that the agent, the kali-sandbox, and you (through the FileSystem Drawer in the Red Zone) all see at the same time. Four purpose-built folders are auto-created and protected from rename/delete: notes/ for the agent's scratch work and draft reports, tool-outputs/ for auto-offloaded huge outputs, jobs/ for background-job logs, and uploads/ for files you drop in for the agent to read. The agent is taught the layout on every think step via a WORKSPACE_LAYOUT_BLOCK, and when you drop files into uploads/ the block surfaces them under a CHECK THESE NOW directive so the agent reads them before continuing whatever else it was doing.

The agent gets 24 filesystem tools (fs_read, fs_write, fs_edit, fs_multi_edit, fs_undo_edit, fs_grep, fs_glob, fs_find, fs_diff, fs_symbols, fs_archive, fs_extract, and more) plus 5 background-job tools (job_spawn, job_status, job_wait, job_cancel, job_list). Long scans like nuclei or hydra detach as asyncio tasks and stream output to jobs/<id>.log, so the agent can fs_grep for hits mid-flight without blocking the next reasoning step. Outputs over 20 KB automatically offload to tool-outputs/<utc-iso>-<tool>.txt and the LLM receives a head/tail stub plus the file path, so a 5 MB Playwright DOM dump never derails the context window. The drawer surfaces all of this with breadcrumb navigation, drag-and-drop upload, inline preview, SHA-256 properties, per-folder tar.gz download, and a Jobs tab with live status badges and cancel.

Path validation rejects every traversal trick (project-id injection, symlink escape, zip-slip, tar-slip, protected-folder bypass via normalization) and is server-enforced. Jobs survive agent restart via on-disk metadata: orphan running jobs flip to interrupted on boot so the UI never shows a forever-spinning row.

Full operator manual (every drawer feature, all 29 workspace tools, the auto-offload policy map, the four protected folders, fireteam coordination patterns via fs_diff vs_last_read, and the path-validation safety model): Agent Workspace wiki page.

The agent's most powerful execution mode. When an objective decomposes into independent investigation angles (auth surface, route map, header policy; or 5 candidate CVEs to triage in parallel), the root agent fans out into N specialist sub-agents that work concurrently inside the same backend, each running its own multi-step ReAct loop with a focused mission. This is RedAmon's implementation of the Scatter-Gather ReAct (SG-ReAct) architectural pattern: a root agent that decides when to fan out, a bounded fireteam of specialists that work in parallel, and a fan-in step that merges their findings back into a single consolidated worldview.

Every safety guarantee that applies to the root agent also applies to every member: hard guardrails, soft guardrails, phase gating, Rules of Engagement, and dangerous-tool confirmations (handled per-member, in parallel; N members can each be awaiting your approval on their own panel simultaneously without serializing). Recursion is forbidden (a member cannot itself deploy a fireteam) and every wave has a hard cap on members, an iteration budget per member, and a wall-clock timeout. The result is wall-clock parallelism without coordination chaos, predictable termination, and an audit trail where every action is attributable to the specialist that produced it.

Wiki: Fireteam (Parallel Specialists) | Technical: README.AGENTIC_SYSTEM.md

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.

Agent in the Loop is not a provider and needs no key: it hands a chat's reasoning to your own Claude Code or Codex over the MCP server (see above).

OpenAI-compatible provider settings include a reasoning effort control. Enable it to send reasoning_effort with low, medium, high, or max; leave it disabled to send nothing and use the model's default. Enable it only for thinking-capable models: a model without the thinking capability rejects a level, and the agent transparently retries without it. The available effort levels are model-dependent. Canonical OpenAI providers and unrelated OpenAI-compatible endpoints keep their existing behavior.

Wiki: AI Model Providers

A Neo4j knowledge graph, the single source of truth for the target's attack surface. Its node types and relationships are declared once, in graph_db/schema_sections.md, and the schema the agent is served is generated from that file. The agent queries it before every decision via natural language → Cypher translation.

Wiki: Attack Surface Graph | Technical: GRAPH.SCHEMA.md

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.

Wiki: EvoGraph | Technical: README.AGENTIC_SYSTEM.md

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.

Wiki: AI Agent Guide

RedAmon's built-in, engagement-scoped proxy history: a credential-free man-in-the-middle proxy (powered by mitmproxy) sits between every offensive tool and its target, records the full request/response of each HTTP transaction, tags it with who produced it (project / user / run / tool via a signed HMAC context tag), and stores it in Postgres through a trusted, INSERT-only ingest worker. Think of an always-on HTTP history, except it turns on with a toggle, attributes every request to its source, and is queryable by the operator and the AI agent.

Capture is off by default and gated at two levels (a global master switch that runs the proxy, plus a per-project routing toggle). Eight recon tools and eight agent HTTP tools (execute_curl, execute_httpx, execute_playwright, execute_nuclei, execute_katana, execute_ffuf, execute_arjun, execute_wpscan) are routed, so both the pipeline's and the agent's own crawl/fuzz/scan traffic is captured, searchable, and replayable. The proxy holds no secrets, an SSRF egress guard with a DNS-rebinding IP pin keeps it from pivoting into internal infrastructure, sensitive headers are redacted, and passive signals (reflected params, missing security headers, cookie-flag issues) are computed for free on every response. A TrafficMind view in the top navigation exposes the corpus as a paginated, filterable, proxy-style table with a request/response detail drawer, CSV/JSON export, and reference-counted body cleanup.

The agent works the corpus through a single code-native tool, proxy_brain: it writes Python against a pre-imported redamon SDK and composes the attack itself (loops, conditionals, crypto, oracles) rather than picking from a fixed menu. The SDK's read calls (search, get, sitemap, params, grep, diff, to_curl, query) run in any phase; its active calls (replay, batch, fuzz) send live traffic and are gated to the exploitation phases, as is browser(id), which drives a real Chromium to confirm bugs that only surface after JavaScript runs (DOM-based XSS, SPA-only routes, JS-minted CSRF). proxy_brain runs in the Kali sandbox but holds no database credential: it reaches the corpus only through the agent's /traffic/exec (read), /traffic/replay (active) and /traffic/browser (browser) endpoints, tenant-scoped by a signed tag the sandbox cannot forge, host-pinned to the origin on every send, budget-capped, stealth-restricted, and re-captured. The agent reads its own on-demand cookbook with redamon.manual(). See docs/readmes/README.TRAFFIC.md for the architecture.

Wiki: TrafficMind | Technical: README.TRAFFIC.md

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.

Wiki: Reverse Shells

Full interactive PTY shell access to the Kali sandbox container directly from the graph page via xterm.js. Access all pre-installed pentesting tools (Metasploit, Nmap, Nuclei, Hydra, sqlmap) without leaving the browser. Features dark terminal theme, connection status indicator, auto-reconnect with exponential backoff, fullscreen mode, and browser-side keepalive.

Wiki: Red Zone (RedAmon Terminal)

Two-agent pipeline. A Triage Agent scores every finding in the graph with a fixed risk model (how likely it is to be real, times how likely it is to be exploited, times how bad that would be, times how reachable it is), groups the findings that share a fix, and has an LLM check the evidence behind each one it can judge. The model corrects the factors and never produces a score, every quote it gives is verified against the evidence it was sent, and it binds no tools. The ranking is complete and correct with no model configured at all. 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. Because the cloned repo is untrusted, its build/test commands run in an isolated, secret-free sandbox container (not in the agent), and the GitHub token never enters it.

Wiki: CypherFix | Technical: README.CYPHERFIX_AGENTS.md

An LLM-powered Intent Router classifies user requests into agent skills: CVE (MSF), SQL Injection, XSS, SSRF, RCE, Path Traversal / LFI / RFI, Credential Testing, Social Engineering, Availability Testing, or custom user-defined skills uploaded as Markdown files. Ready-to-use community skills ship for API testing, XSS, SQLi, XXE, BFLA, SSTI, IDOR / BOLA, insecure deserialization, mass assignment, subdomain takeover, and insecure file uploads -- download the .md file and upload it via Global Settings > Agent Skills (or a project's Agent Skills section), one file or a batch, to activate it for your user. You can also contribute your own by opening a PR.

Wiki: Agent Skills | Community Skills

On-demand reference injection via /skill command in the agent chat. Chat Skills are tactical reference docs -- tool playbooks, vulnerability guides, framework-specific notes -- that you inject into the agent's context exactly when you need them. Type /skill ssrf to load SSRF expertise, or click the skill picker button for a browsable list. 46 reference skills ship with RedAmon covering vulnerabilities (JWT, OAuth/OIDC, CSRF, race conditions, business logic, prototype pollution, ReDoS, 2FA bypass, LDAP/XPath injection, web cache poisoning, CORS, host header injection, clickjacking, CRLF, and more), tooling (sqlmap, nuclei, ffuf, nmap, httpx, naabu, katana, subfinder, semgrep), protocols (GraphQL, WebSocket, SOAP/WS-Security, SAML), technologies (Firebase, Supabase), frameworks (Next.js, FastAPI, NestJS), Active Directory (kill chain, Kerberoasting/ASREPRoast, AD-CS ESC1-15, BloodHound path-to-DA), cloud (AWS, Azure, GCP), and post-exploitation (Docker escape, Linux / Windows privesc). Unlike Agent Skills (which drive classification and phase-aware workflows), Chat Skills are supplementary context that persists until you change or remove them.

Wiki: Chat Skills | Community Chat Skills

A plugin platform, part of every install (which is why RedAmon needs Docker Engine 28+), lets new capabilities ship as plugins from the separate, public redamon-plugins repository instead of changes to RedAmon itself. An admin installs a plugin from the Plugins page, out of a signed catalog or from files; its actions then appear where it declares them (the chat's gear menu, a project's skills row, its own page), each marked with a plugin badge. The first plugin, Skiller, reads one finished chat session and proposes a better, session-agnostic version of a skill the agent used, built-in or one of your own uploaded .md skills (you pick which). You review it side by side: a built-in skill's version is approved, rejected, or reset later; a version of your own skill is saved as a new skill, named <name> vN by default, and the original is never changed.

Plugin code is treated as untrusted: it runs in a separate runner container, one process and UID per plugin, with no internet and no credentials, and reaches RedAmon only through a Gateway that checks a per-call token, the plugin's granted permissions, and your tenancy on every call. A plugin can read only what it was granted, keep its own data, ask the agent to call your chosen model for it, and propose skill text; nothing it proposes changes the agent until a person approves it.

Wiki: Plugins | Technical: README.PLUGINS.md | Plugin SDK: README.PLUGIN_SDK.md

Scans GitHub repositories, gists, and commit history for exposed secrets using 40+ regex patterns and Shannon entropy analysis.

Wiki: GitHub Secret Hunting

Hunts live credentials across 14 kinds of target with 1060 detectors: git repositories, GitHub (including deleted commits), GitLab, Docker registries, Hugging Face, S3, GCS, a local filesystem, Jenkins, Elasticsearch, Postman, CircleCI and Travis CI. It goes one step past a regex scanner by calling the owning service's API with the credential it found, so a finding says whether the secret is actually still live, dead, or never checked. Each source is configured once per project and runs in its own hardened container (isolated network, read-only root, non-root, exactly one credential and no graph access), so different sources scan in parallel. Results are stored as MultiscannerScan → MultiscannerRepository / Image / Model / Bucket / Endpoint → MultiscannerFinding nodes and surface in the Red Zone secrets table, live findings first. Configure it in project settings, start it per source from the "Other Scans" modal.

Wiki: Secret Multiscanner

Detects known-malicious (MAL-) and known-vulnerable (CVE/GHSA) packages fully offline against a local OSV database, across three layers that share one engine and one graph model. L1 audits an uploaded SBOM / lockfile from the "Other Scans" modal; L2 (Supply-Chain Recon) harvests the npm package set a live target actually serves during recon (source maps, imports, technologies) with zero manifest; L3 gives the AI agent on-demand execute_osv_scanner / execute_guarddog tools. Untrusted bytes (tarballs, target JS) are processed in a hardened, secret-free, network-isolated DIRTY sandbox (cap_drop=ALL, read-only, no-install); only a schema-validated JSON artifact crosses into the creds-holding writer. Results are stored as Package / MalPackageFinding nodes (MAL- = malicious, CVE/GHSA = vulnerable, GuardDog = suspicious). Populate the offline DB once with ./redamon.sh supply-chain-sync npm.

Technical: README.SUPPLY_CHAIN.md

Hundreds of configurable parameters across 16 tabs controlling every tool's behavior, from scan modules to agent approval gates. Managed through the webapp UI; the generated Project Settings Registry lists every one with its meaning and the values it accepts.

Wiki: Project Settings Reference

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.

Wiki: Rules of Engagement

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.

Wiki: Insights Dashboard

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. Government, military, educational, and international organization domains (.gov, .mil, .edu, .int) are permanently blocked by a deterministic hard guardrail that cannot be disabled.

Wiki: Creating a Project

Per-tool human-in-the-loop gate for dangerous operations. When enabled, the agent pauses before executing high-impact tools (Nmap, Nuclei, Metasploit, Hydra, Kali shell, code execution) and presents an inline Allow / Deny prompt in the chat timeline. Supports both single-tool and parallel-wave (plan) confirmation modes. Users can approve, reject, or modify tool arguments before execution proceeds. Disabled via the Require Tool Confirmation toggle in Project Settings.

Technical: README.AGENTIC_SYSTEM.md (Tool Confirmation Gate)

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.

Wiki: Pentest Reports

Full project backup and restore through the web interface: settings, conversations, graph data, recon/GVM/GitHub hunt results as a portable ZIP archive.

Wiki: Data Export & Import

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]
        PluginRunner[Plugin Runner<br/>isolated network, no internet]
    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]
        Multiscanner[Secret Multiscanner<br/>14 Sources · 1060 Detectors]
    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]
        SourceAPIs[Secret Sources<br/>GitLab · Docker · S3 · GCS<br/>Hugging Face · CI · ...]
    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
    PluginRunner <-->|Gateway, via plugin-gateway proxy| Webapp
    Webapp --> Neo4j
    Webapp --> Postgres
    ReconOrch -->|Docker SDK| Recon
    ReconOrch -->|Docker SDK| GVM
    ReconOrch -->|Docker SDK| GHHunt
    ReconOrch -->|Docker SDK, one per source| Multiscanner
    ReconOrch -->|Multiscanner ingest| Neo4j
    Recon -->|Fetch Settings| Webapp
    GHHunt -->|GitHub API| GitHubAPI
    Multiscanner -->|GitHub API| GitHubAPI
    Multiscanner --> SourceAPIs
    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

RedAmon is fully Dockerized and runs on any OS with Docker Engine 28.0.0 or newer and Docker Compose v2+. For OS-specific fixes (Linux, Windows, macOS), see Troubleshooting Guide or the Wiki.

Want to see RedAmon think like a real pentester? Explore real-time live attack sessions -- every step, every pivot, every exploit -- across 15 vulnerability categories on a live target. Full session logs, decoded walkthroughs, and video recordings showing the agent autonomously compromising a multi-service server from scratch. Explore the HackLab →   |   Submit your own session → Got an amazing agent session on your own target? Share it with the community -- session log + YouTube video.

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.

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: [email protected]

Sponsorship: RedAmon is free and MIT licensed, and stays that way. If you would like to sponsor the project, write to the same address. Sponsorship helps cover development and testing costs.

Local by default; server deployment has a supported hardened path. Out of the box RedAmon is meant to run on a local machine and does not include internet-facing security controls on its own. To run it on a public, internet-reachable server, use the hardened single-host deploy in tooling/deploy/single-host/, which puts the whole stack behind nginx + TLS, a host firewall, SSH hardening, and a single public HTTPS origin, with every internal service bound to loopback. Running the raw stack (without that deploy) on a public IP would expose unauthenticated internal services, so anything outside a trusted local network without the hardened deploy is entirely at your own risk.

This project is released under the MIT License.

RedAmon integrates several third-party tools under their own licenses (MIT, Apache-2.0, BSD, GPL-2.0/3.0, AGPL-3.0, LGPL, and the WPScan Public Source License). Source code for all AGPL-licensed components is available at their upstream repositories. The full inventory and license obligations are documented in THIRD-PARTY-LICENSES.md.

Commercial use note: The Kali sandbox image bundles WPScan, which is governed by the WPScan Public Source License. WPScan restricts commercial use (SaaS, paid product offerings, value-added services) without a separate license from the WPScan team. Pentesting engagements and personal use are permitted. If you intend to use RedAmon in a commercial product or service, review THIRD-PARTY-LICENSES.md before distribution.

See DISCLAIMER.md for full terms of use, acceptable use policy, and legal compliance requirements.

Use responsibly. Test ethically. Defend better.