A tree-sitter based AST difftool to get meaningful semantic diffs

Enlightened library to convert HTML and CSS to SVG

Scalable toolkit for efficient model reinforcement

SkyRL: A Modular Full-stack RL Library for LLMs

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Official Implementation of Paper Transfer between Modalities with MetaQueries

verl: Volcano Engine Reinforcement Learning for LLMs

A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.

Data transformation framework for AI. Ultra performant, with incremental processing.

Access large language models from the command-line

An extremely fast Python type checker and language server, written in Rust.

Time-Series-Optimized Transformer for Observability

Easiest way to give context to LLMs; Attachments has the ambition to be the general funnel for any files to be transformed into images+text for large language models context by only adding 2 lines …

Extract the main content from web pages.

Lightweight coding agent that runs in your terminal

AI SYSTEMS TRANSPARENCY FOR ALL! - LEAKED SYSTEM PROMPTS FOR CHATGPT, GEMINI, GROK, CLAUDE, PERPLEXITY, CURSOR, WINDSURF, DEVIN, REPLIT, AND MORE!

LLVM-based Solidity compiler.

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!

List of the public smart contract audit reports and security reviews performed by Hexens.

A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training

Official inference framework for 1-bit LLMs

Code for BLT research paper

Deploy any app to TEE.

Commonware Library Primitives and Examples

A minimal (and wicked fast) blockchain built with the Commonware Library.

Gemma open-weight LLM library, from Google DeepMind

lightweight, standalone C++ inference engine for Google's Gemma models.

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation