AI Agents
Anthropic-Cybersecurity-Skills
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fr…
★ 33.8k starsApache-2.0
View guide →// agents · samugit83/redamon
redamon
redamon is an open-source agents project by samugit83 (samugit83/redamon on GitHub). It has 2,918 GitHub stars and 597 forks, is released under the MIT license, and was last updated on GitHub on 3 October 2026.
Self-hosted AI pentesting agent that finds flaws and opens PRs to fix them.
💎 Hidden gem★ 2.9k stars⑂ 597 forksMITupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- samugit83/redamon
- GitHub stars
- 2,918
- Forks
- 597
- License
- MIT
- Last updated on GitHub
- 3 October 2026
- Category
- Agents
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Define the target
Scope the systems RedAmon is allowed to test.
- Map the attack surface
It builds a graph of reachable assets.
- Approve the exploits
Autonomous attacks run behind human gates.
- Merge the fixes
RedAmon opens pull requests for the flaws it finds.
// features
Why people love it
Autonomous exploitation
Finds and tests real vulnerabilities.
Kali sandbox
Attacks run in an isolated environment.
Human approval gates
Nothing sensitive runs without a yes.
Auto-fix pull requests
Vulnerabilities become fix PRs.
MCP both ways
Use MCP tools, or drive it via MCP.
Attack-surface graph
A visual map of what is exposed.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/samugit83/redamon.git cd redamon - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project’s launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Pentest a web app before launch.
- Continuously scan your attack surface.
- Auto-generate fix PRs for findings.
- Run bug-bounty-style recon autonomously.
Advertisement
// faq
Questions, answered
Who maintains RedAmon?
It is an open-source project at samugit83/redamon with 597 forks. Check activity before relying on it.
Is RedAmon free for commercial use?
Yes. MIT licensed.
Is it legal to run?
Only against systems you own or have written permission to test.
Do I need Kali Linux?
Attacks run from a Kali sandbox the framework manages.
Can it really fix what it finds?
It opens PRs with proposed fixes; a human still reviews and merges.
// keep exploring
Similar tools
AI Agents
browser-agent
Open-source, vision-first browser agent
★ 4.1k starsApache-2.0
View guide →AI Agents
nanobot
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat…
★ 48.8k starsMIT
View guide →AI Agents
open-multi-agent
Open Multi Agent — a self-hosted TypeScript agent runtime with durable approvals and verifiable run records.
★ 7.0k starsMIT
View guide →AI Agents
Rakazo
Rakazo — an open-source, self-hosted AI agent for persistent teammates: bring your own model and computer, run it on web, desktop, iPhone and Android
★ 4.1k starsApache-2.0
View guide →AI Agents
CoreCoder
Self-hosted ai agents: minimal ai coding agent (~1,000 lines of python) inspir.
★ 1.8k starsMIT
View guide →// alternatives
Alternatives in Agents
The most-starred other Agents projects in the LibreAI catalogue — the realistic shortlist if redamon is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in Agents
Nearby Agents projects in the catalogue, closest in stars to redamon — keep exploring the shelf either side of it.
- eventcatalog★ 2.9k
Living architecture documentation that both your team and AI agents can read.
- agent-rules-books★ 2.9k
Battle-tested coding rules for AI agents, distilled from classic programming books.
- forkd★ 2.9k
Fork() for AI agent microVMs — spawn 100 KVM-isolated children in ~100ms from a warm parent
- CloddsBot★ 2.9k
Autonomous AI trading agent spanning 1000+ markets, from Polymarket to Solana DEXs.
- memobase★ 2.9k
User-profile-based long-term memory for AI chatbot applications
- moltis★ 2.9k
Secure persistent personal agent server in one Rust binary — sandboxed, multi-provider, on your hardware
Get redamon
Free and open — grab the source, star the repo, and start creating.