LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.

A domain-specific probabilistic programming language for scalable Bayesian data cleaning

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

A lightweight data processing framework built on DuckDB and 3FS.

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Wan: Open and Advanced Large-Scale Video Generative Models

DeepEP: an efficient expert-parallel communication library

Automatically convert epubs to audiobooks

OctoTools: An agentic framework with extensible tools for complex reasoning

Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.

A production-ready LLM-Powered Node.js & TypeScript REST API template, with a focus on Clean Architecture

free and open OpenAI Deep Research

An open-source runtime for composable workflows. Great for AI agents and CI/CD.

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

A simple screen parsing tool towards pure vision based GUI agent

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

🪄 Create rich visualizations with AI

Open-source graph database, tuned for dynamic analytics environments. Easy to adopt, scale and own.

The largest Open-Source UI Library! Community-made and free to use. Made with either CSS or Tailwind.

Chat with your Logseq knowledge base powered by local LLM.

Synthetic Data SDK ✨

A Chrome extension for asking questions over websites

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…

Gen AI Toolbox for Databases is an open source server that makes it easier to build Gen AI tools for interacting with databases.