Lists (12)
Stars
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
Toolkit designed to parse complex source code and transform it into a rich, structured, and queryable knowledge graph
Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …
Claude Code, Codex, and Grok interfaces as shadcn components
Desktop app to generate 3D models from images using local AI — runs entirely on your GPU
Android Phone Control With Qwen3-VL
Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Playwright Model Context Protocol Server - Tool to automate Browsers and APIs in Claude Desktop, Cline, Cursor IDE and More 🔌
Dusseldorf is an out-of-band security tool to help in security research.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
Vane is an AI-powered answering engine.
Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents
The Context Platform for your Data and AI Stack
A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search
Real-time OSINT command center monitoring the Middle East conflict — 50+ live open-source intelligence sources (news, Telegram, military aircraft & naval tracking, missile alerts, prediction & defe…
Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT GPT-5.6, Codex GPT-5.6, GPT-5.5. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xA…
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
Companion code for the global workspace interpretability paper
Autonomous game development for Godot, Bevy, and Babylon.js with Claude Code and Codex
A lightweight, lightning-fast, in-process vector database
autonomous red teaming platform; multi-agent offensive-security meta-harness