Stars
Claude Agent SDK with a web browsing tool
Run Claude Code safely in local Docker containers without having to approve every permission
AI agents that read papers and create datasets
Verified kernels, written in Dafny and compiled to JavaScript, for correct-by-construction state in interactive web applications
AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions, and synthesize the best approach for your code.
Problem solving by engaging multiple AI agents in conversation with each other and the user.
Statue: Svelte + Markdown Static Site Generator, launch a website for your business, blog, portfolio, or product in seconds, with one-line setup
Collector is an ORM, CRUD server, and distributed programming project using protobufs, grpc, sqlite, and extensive use of reflection!
Obsidian vault template with SKIF protocol, PSP framework, and Claude AI integration
A local-first memory layer for AI (Cursor, Zed, Claude). Persistent architectural context via semantic search.
Information hub for our project training the largest possible historical LLMs.
A unified interface for AI in your terminal.
Automate anything with Codex CLI in a local Docker container with cron, file watchers, webhooks, search/indexing, speech, and hundreds of tools on tap.
Kosmos: An AI Scientist for Autonomous Discovery - An implementation and adaptation to be driven by Claude Code or API - Based on the Kosmos AI Paper - https://arxiv.org/abs/2511.02824
The contents of /home/oai/skills in ChatGPT's code interpreter environment
Various scripts I wrote when using FreeBSD/Linux/UNIX systems for 15+ years.
Self-improving AI: Transform CLAUDE.md into a learning system. One prompt makes Claude learn from every mistake. Meta-rules + reflection = continuous improvement.
This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.
Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.
CLI that makes Google Gemini the lead architect for Claude Code. Multi-model AI pair programming.
SynthLang is a hyper-efficient prompt language designed to optimize interactions with Large Language Models (LLMs) like GPT-4o by leveraging logographical scripts and symbolic constructs.