# CyberStrikeus/CyberStrike

Open-source AI-powered offensive security harness for automated penetration testing.

Repository: https://github.com/CyberStrikeus/CyberStrike
Canonical: https://ross.abutalabs.com/products/cyberstrike
Homepage: https://cyberstrike.io
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: agents, ai-hacking, ai-penetration-testing, ai-pentesting, ai-security, artificial-intelligence, bug-bounty, code-quality, ctf-tools, cybersecurity, cybersecurity-tools, ethical-hacking, hacking, llm-security, offensive-security, penetration-testing, pentesting-tools, red-teaming, security, security-automation
Last push: 2026-08-26T12:33:22+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 14
- inputs: {"age_days": 200, "days_push": 7, "days_rel": 20, "gap_med": 5, "n_releases_24m": 14}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2043, forks 308 (observed 2026-08-28T04:06:08.549751+00:00)

## What it is
CyberStrike is an open-source AI-powered offensive security harness that runs automated penetration testing from the terminal. It orchestrates 13+ specialized agents, 7,600+ security skills, and 120+ OWASP test cases using any of 150+ LLM providers, with remote tool execution via Bolt servers and MCP tool integration.

## Use cases
- automate penetration testing with AI agents
- run autonomous red team assessments from the terminal
- find web vulnerabilities with OWASP test cases
- use my LLM subscription for security testing
- orchestrate recon and post-exploitation agents
- run pentesting on remote VPS or Kali boxes
- prepare for bug bounty hunting with AI assistance

## When to choose
- you want an open-source, extensible AI pentesting agent that works with many LLM providers
- you need specialized agents for recon, web, network, cloud, and post-exploitation
- you want remote tool execution across multiple Bolt servers
- you need OWASP-aligned automated test coverage and generated reports

## When to avoid
- you need a passive vulnerability scanner without autonomous attack actions
- you cannot legally or ethically run offensive tooling against your targets
- you require a GUI-only workflow without terminal or CLI usage
- you need guaranteed safety guardrails over an autonomous agent with broad tool access

## Facets
- artifact type: cli-tool
- maturity: active
- function: penetration-testing, agent-framework, llm-inference, mcp, security, cli, workflow-automation
- domain: security, penetration-testing, artificial-intelligence, developer-tools
- platform: windows, cli, self-hosted
- tags: offensive-security, red-teaming, ai-pentesting, bug-bounty, ctf-tools, ethical-hacking, llm-security, security-automation, autonomous-agents, ai-agents, command-line, macos, linux, nodejs, docker

## Member repositories
- CyberStrikeus/CyberStrike (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:08.549751+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:58:05.850033+00:00, confidence not recorded.
  - readme: https://github.com/CyberStrikeus/CyberStrike (fetched 2026-08-28T04:06:08.549751+00:00, sha 09811f446055)
  - homepage: https://cyberstrike.io (fetched 2026-08-29T10:38:27.993275+00:00, sha 86e323a483b6)
- Data as of 2026-08-30T08:39:29.467469+00:00.