The best ChatGPT that $100 can buy.

Simplifying reinforcement learning for complex game environments

♟️ Vectorized RL game environments in JAX

Training Sparse Autoencoders on Language Models

Local first semantic and hybrid BM25 grep / search tool for use by AI and humans!

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

A curated list of awesome environments and training frameworks for Reinforcement Learning (RL), organized by domain.

Python JSON parser for reading JSON objects out of JS files

Synthetic Patient Population Simulator

VerbNet semantic parser and related utilities

A thesaurus of predicates.

Evaluating modern LLMs on offensive-cybersecurity tasks with METR-style time-horizon analysis.

Allows AI agents (e.g., Cursor, Claude Code) to debug within Tauri apps via screenshot capture, window management, DOM access, and simulated user inputs.

Secure and fast microVMs for serverless computing.

Python client and types generator for the Chrome DevTools Protocol (CDP)

Reinforcement Learning tutorials with Metadrive: A collection of hands-on notebooks and resources to get started with reinforcement learning using the powerful MetaDrive simulation environment.

Landing page for evaluation awareness

A Lean tactic for Canonical, a search procedure for terms in dependent type theory.

A dialect of Lisp that's embedded in Python

Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

A free and opensource platform for studying the artificial language Lojban.

mimalloc is a compact general purpose allocator with excellent performance.

VNC client web application

Charged Peforator

A familiar X11 panel/dock to ease new linux users transition

A TTS model capable of generating ultra-realistic dialogue in one pass.