Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

Run iOS/ macOS in Qemu. Virtual iPhone 17, 16, 15, 14, 13, 12 and M5-M1 Apple Si Macs supported.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Undetectable offensive toolkit inside Chrome

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills b…

Documentation on building an at home budget 48 GB VRAM AI server.

TradingAgents: Multi-Agents LLM Financial Trading Framework

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

EAA is a curated catalog of techniques and real-world cases involving abuse of local AI agents through their runtime, configuration, state, tools, and inherited authority.

WinDBG tool for AI agents

Free email OSINT tool, 2500+ platforms, identity clustering, breach detection. No API keys required. pip install mailaccess

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

A Windows Named Pipe Multi-tool / Proxy

Research notes on Windows Component Object Model (COM) attack surface for offensive security and vulnerability research. Covers COM hijacking, elevation of privilege, DCOM lateral movement, and per…

autonomous red teaming platform; multi-agent offensive-security meta-harness

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei, SQLMap, Hashcat and more.

Jailbreaker is a local evaluation tool for testing chatbot and agent-style systems against jailbreak, prompt-injection, and related failure modes.

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we confi…

Send and receive SMS messages using your Android phone programmatically via a simple HTTP API

An overview of LLMs for cybersecurity.

The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers across function-level, repository-level, agentic, a…