free and open OpenAI Deep Research

Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieval Results in RAG Systems (WWW 2025)

Knowledge Graph Retrieval Augmented Generation (KG-RAG) Eval Datasets

chunkipy is an extremely useful tool for segmenting long texts into smaller chunks, based on either a character or token count. With customizable chunk sizes and splitting strategies, chunkipy prov…

This repository presents the original implementation of LumberChunker: Long-Form Narrative Document Segmentation by André V. Duarte, João Marques, Miguel Graça, Miguel Freire, Lei Li and Arlindo L.…

Project for the Tools For Thought Hackathon at AGI House

A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.

🍱 semantic-chunking ⇢ semantically create chunks from large document for passing to LLM workflows

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/mEkkMXFG

Awesome LLM compression research papers and tools.

An open-source framework for training large multimodal models.

Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch

Effortless Real-Time Sign Language Translation

Python library & framework to build custom translators for the hearing-impaired and translate between Sign Language & Text using Artificial Intelligence.

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Fine Tuning Multimodal LLM "Idefics 9B" on Pokemon Go Dataset available on Hugging Face.

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

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, and more.

Access large language models from the command-line

Generative UI in your terminal

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progres…

Turn any webpage into structured data using LLMs

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/