Stars
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
一款内网综合扫描工具，方便一键自动化、全方位漏扫扫描。(An intranet comprehensive scanning tool, enabling one-click automated, all-round vulnerability scanning)
Collaborator is a place to create with agents.
Reference parser and interpreter for the Dogwood policy language
W3b0s1nt (WebOSINT) is a Python tool/script for passive Domain Intelligence gathering.
[CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.
Lightweight, no vpn firewall solution for Android 11+
AI-powered stock trading backtesting system with LLM-based decision analysis, FastAPI backend, and Next.js frontend.
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 Fraud) · agentskills.io standard · Works w…
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchma…
End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.
A sorted and updated list of security wargame sites.
An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack
ARVO: an Atlas of Reproducible Vulnerabilities in Open source software.
A powerful and user-friendly binary analysis platform!
Share an AI agent as a URL — runs locally in your browser via WebGPU. No server, no account, no install.
Agent skills for search, RAG, and document parsing with Mixedbread. Install with: npx skills add mixedbread-ai/skills
Homomorphic Encryption demos
slime is an LLM post-training framework for RL Scaling.
A next-gen FOSS self-hosted unified zero trust secure access platform that can operate as a remote access VPN, a ZTNA platform, API/AI/MCP gateway, a PaaS, an ngrok-alternative and a homelab infras…
BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.
Meta-Framework of Spatiotemporal Composability