The python library for real-time communication

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

DeepEP: an efficient expert-parallel communication library

AdalFlow: The library to build & auto-optimize LLM applications.

Generalist and Lightweight Model for Text Classification

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

The only open-source toolkit that can download EDGAR financial reports and extract textual data from specific item sections into nice and clean JSON files.

MTEB: Massive Text Embedding Benchmark

A simple screen parsing tool towards pure vision based GUI agent

s1: Simple test-time scaling

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

Stable Diffusion web UI

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.

Supercharge Your LLM Application Evaluations 🚀

The most advanced AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

A Comprehensive Benchmark for Document Parsing and Evaluation

Prompt, run, edit, and deploy full-stack web applications using any LLM you want!

Textbook on reinforcement learning from human feedback

Python tool for converting files and office documents to Markdown.

Instagram Ai Agent 🌸 is built using Node.js and TypeScript 🛠️, designed for seamless job execution 📸. It's lightweight, efficient, and still evolving 🚧—exciting new features coming soon! 🌟

Yi-1.5 is an upgraded version of Yi, delivering stronger performance in coding, math, reasoning, and instruction-following capability.

Knowledge Agents and Management in the Cloud

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Things you can do with the token embeddings of an LLM