[opensourcedex]

CyberStrike is a free, open source ai security & privacy project written in TypeScript and released under AGPL-3.0. It has 2,797 GitHub stars, 429 forks and 43 open issues, and was last pushed 7 hours ago. On this registry it ranks #11 of 34 tracked projects in AI Security & Privacy, with 5 head-to-head comparisons available. It gained 36 stars over the last 3 tracked days.

What is CyberStrike?

What it is

CyberStrike is open-source TypeScript project. It is AI-powered offensive security harness. It lives in AI & Machine Learning / AI Security & Privacy ecosystem. It targets automated penetration testing. It solves problem of turning general AI model into red team agent. It uses terminal TUI. It connects Claude, GPT, or any LLM subscription. It handles reconnaissance, vulnerability discovery, exploitation, and reporting autonomously. It has 13+ specialized agents, 7,600+ security skills, and 120+ OWASP test cases. It supports 150+ AI providers, 5,300+ models, 56+ built-in tools, and 176+ MCP tools. It has 2746 stars, 419 forks, and 43 open issues.

CyberStrike is not just wrapper around LLM. It is intelligence layer. It injects OWASP testing methodology, vulnerability patterns, attack chain reasoning, and tool orchestration logic into every interaction. It normalizes schema, guards context, detects provider, and chains tools based on findings. It lets existing AI subscription power pentest toolkit. README says no separate API costs.

Key capabilities

  • CyberStrike runs 13+ specialized agents for offensive security workflows.
  • CyberStrike includes 7,600+ security skills and 120+ OWASP test cases.
  • CyberStrike connects 150+ AI providers and 5,300+ models through bundled SDK providers and models.dev catalog.
  • CyberStrike exposes 56+ built-in tools and 176+ MCP tools for tool orchestration.
  • CyberStrike injects OWASP methodology, vulnerability patterns, attack chain reasoning, and tool orchestration logic into LLM interactions.
  • CyberStrike normalizes structured output across providers, guards context, detects provider endpoints, and chains security tools based on findings.

Who uses it and how

  • Security engineers use terminal TUI to tell CyberStrike what to test, then let it handle reconnaissance, vulnerability discovery, exploitation, and reporting.
  • Bug bounty hunters use topics bug-bounty, ethical-hacking, and CTF-tools to run automated pentest and CTF workflows.
  • Red team operators use existing Claude, GPT, Gemini, Bedrock, Azure OpenAI, Vertex AI, GitHub Copilot, xAI, Groq, Mistral, DeepSeek, Cerebras, Cohere, OpenRouter, Together AI, DeepInfra, Perplexity, Alibaba Cloud, Cloudflare AI Gateway, or Ollama subscriptions or API keys.
  • Teams use models.dev catalog and 23 bundled SDK providers to connect many AI endpoints.
  • Users use docs.cyberstrike.io and cyberstrike.io for demos and guides.

Getting started

Install CyberStrike with npm i -g @cyberstrike-io/cyberstrike@latest, then run cyberstrike. First run asks for LLM provider and API key, then launches terminal TUI.

When to use it — and when not to

Use CyberStrike when teams want open-source AI pentest automation on top of existing LLM subscription, and they accept AGPL-3.0 license. Do not use it when teams need managed hosted service, because README shows npm install and local terminal TUI, not hosted option. Do not use it when teams need mature contributor signal, because contributors field is empty, repo age is 1 years, and open issues are 43.

project readme (upstream, from github) — read inline

English | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Dansk | 日本語 | Polski | Русский | Bosanski | العربية | Norsk | Português (Brasil) | ไทย | Türkçe | Українська | বাংলা | Ελληνικά | Tiếng Việt | हिन्दी

The first open-source AI agent built for offensive security.

Automated penetration testing from your terminal — plug in your Claude, GPT, or any LLM subscription
and turn it into an autonomous red team agent with 13+ specialized agents, 7,600+ security skills, and 120+ OWASP test cases.
150+ AI providers • 5,300+ models • 56+ built-in tools • 176+ MCP tools

Quick Start • Intelligence Layer • What Makes It Different • Agents • Skills • Web UI • Bolt • MCP Ecosystem • Post-Exploitation • Installation • Docs • Website

npm Downloads Build Discord License

Quick Start

npm i -g @cyberstrike-io/cyberstrike@latest && cyberstrike

That's it. CyberStrike launches a TUI in your terminal, asks for your LLM provider and API key on first run, and you're ready to go. Tell it what to test — it handles reconnaissance, vulnerability discovery, exploitation, and reporting autonomously.

Already have a Claude Code or OpenAI subscription? CyberStrike's intelligence layer sits on top of your existing AI subscription. No separate API costs — your current plan powers an entire pentest toolkit.

Explore the full documentation at docs.cyberstrike.io or visit cyberstrike.io for demos and guides.

Intelligence Layer

CyberStrike isn't just a wrapper around an LLM. It's an intelligence layer that transforms any AI model into an offensive security specialist.

How it works: When you connect your LLM provider, CyberStrike injects domain-specific context — OWASP testing methodology, vulnerability patterns, attack chain reasoning, and tool orchestration logic — into every interaction. The model doesn't need to know security; CyberStrike teaches it.

What the intelligence layer provides:

  • Schema normalization — Structured output from any provider, regardless of response format differences
  • Context guard — Prevents prompt leakage and keeps the agent focused on the current test phase
  • Provider auto-detection — Automatically identifies your LLM endpoint and configures the optimal transport
  • Tool orchestration — Chains security tools intelligently based on findings, not fixed scripts

150+ AI providers and 5,300+ models supported out of the box:

CyberStrike integrates with the entire AI ecosystem through 23 bundled SDK providers and 150+ providers via the models.dev catalog. Here are the core integrations:

Provider Models Notes
Anthropic Claude 4.5, Claude 4 Best performance with extended thinking
OpenAI GPT-5, GPT-4.1, o3, o4 Full tool-use + reasoning support
Google Gemini 2.5 Pro/Flash Long context for large codebases
Amazon Bedrock All Bedrock models IAM auth, no API keys needed
Azure OpenAI All Azure-hosted models Enterprise deployments
Google Vertex AI Gemini + Claude on GCP Regional endpoints (EU/US)
GitHub Copilot GPT-5, Claude, Gemini Use your existing Copilot subscription
xAI Grok 3, Grok 3 Mini Real-time data access
Groq LLaMA, Mixtral Ultra-fast inference
Mistral Mistral Large, Codestral European data residency
DeepSeek DeepSeek V3, R1 Cost-effective alternative
Cerebras LLaMA on Cerebras Fastest inference available
Cohere Command R+ RAG-optimized models
OpenRouter 300+ models Single API, any model
Together AI Open-source models Fine-tuning support
DeepInfra Open-source models Pay-per-token, no GPU needed
Perplexity Sonar models Search-augmented generation
Alibaba Cloud Qwen, Kimi, DashScope Chinese model ecosystem
Cloudflare AI Gateway Any provider via gateway Caching, rate limiting, analytics
Ollama Any GGUF model Fully offline, local-only
LM Studio Any local model Desktop GUI + API server
vLLM Any HuggingFace model Self-hosted, GPU-optimized
Any OpenAI-compatible — Custom endpoints welcome

Air-gapped environments? Run CyberStrike entirely offline with Ollama or LM Studio. No data leaves your machine — ever.

What Makes It Different

Specialized Security Agents, Not Generic Chat

CyberStrike ships with 13+ agents purpose-built for security domains. Each agent carries domain-specific methodology, tool knowledge, and testing patterns. The web-application agent follows OWASP WSTG. The cloud-security agent knows CIS benchmarks. The mobile agent uses Frida and follows MASTG/MASVS. They don't guess — they follow proven offensive security frameworks.

Intelligence Layer, Not Just an LLM Wrapper

Most AI security tools are thin wrappers that send your prompt to an API. CyberStrike's intelligence layer normalizes outputs across 150+ providers and 5,300+ models, guards context between test phases, auto-detects your provider configuration, and orchestrates multi-step attack chains. The result: consistent, methodology-driven pentesting regardless of which model you use.

150+ Providers, Zero Lock-in

Anthropic, OpenAI, Google, Amazon Bedrock, Azure, Groq, Mistral, xAI, DeepSeek, Cerebras, Cohere, OpenRouter, Toget

readme truncated — read the full docs on github

Frequently asked questions

Is CyberStrike free to use?

CyberStrike is open source under the AGPL-3.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does CyberStrike do?

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

What is CyberStrike written in?

CyberStrike is primarily written in TypeScript. Its source is publicly available at https://github.com/CyberStrikeus/CyberStrike, and it has 2,797 GitHub stars.