An AI benchmark for creative, human-like problem solving using Sudoku variants

Marco Search Agent for Realistic and Challenging Agentic Search

Source code for extensions in the official PopClip Extensions directory.

verl: Volcano Engine Reinforcement Learning for LLMs

Autonomous program improvement

Code snippets to reproduce MCP tool poisoning attacks.

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

OpenTelemetry collector

Collection of leaked system prompts

DSPy: The framework for programming—not prompting—foundation models

A collection of GPT system prompts and various prompt injection/leaking knowledge.

SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

🔍 Explore what happens under the hood with the ChatGPT web app, its backend API calls and more. And some speculation, of course.

AI Browser

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.

An experimental open-source attempt to make GPT-4 fully autonomous.

fast-stable-diffusion, +25-50% speed increase + memory efficient + DreamBooth

FoodAdvisor starter (Strapi v4 + Next.js) in a Turborepo with Docker Compose.

uBlock Origin - An efficient blocker for Chromium and Firefox. Fast and lean.