Stars
MCP server for Google search and page fetching using headless Chromium
Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
bloom - evaluate any behavior immediately 🌸🌱
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
🚀 Lightweight Python library for building production LLM applications with smart context management and automatic token optimization. Save 10-20% on API costs while fitting RAG docs, chat history, …
Open, Multi-modal Catalog for Data & AI
Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages
🤗 smolagents: a barebones library for agents that think in code.
🌸 Best framework to build web agents, and deploy serverless web automation functions on reliable browser infra.
A website where you can compare every AI Model ✨
A visual playground for agentic workflows: Iterate over your agents 10x faster
Easy token price estimates for 400+ LLMs. TokenOps.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API
High-performance open-source in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. Cypher-compatible, built in C++.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Official Github repository for the SIGCOMM '24 paper "Accelerating Model Training in Multi-cluster Environments with Consumer-grade GPUs"
A streamlit component to embed video and music players from various websites.
Refacer: One-Click Deepfake Multi-Face Swap Tool
IA3방식으로 KoAlpaca를 fine tuning한 한국어 LLM모델
VectorHub is a free, open-source learning website for people (software developers to senior ML architects) interested in adding vector retrieval to their ML stack.
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.