Stars
Cited 83-model x 49-benchmark LLM evaluation matrix with 18 matrix completion methods
An open-source AI agent that brings the power of Gemini directly into your terminal.
TrustRAG：The RAG Framework within Reliable input,Trusted output
GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or…
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
[EMNLP 2025 Demo] Extracting internal representations from vision-language models. Beta version.
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Self & Semi-Supervised Speech Domain Adaptation
The simplest, fastest repository for training/finetuning small-sized VLMs.
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Academic website template that pulls your google scholar publications. You will need to update the files, enable github pages, and enable the google scholar stats workflow for it to work properly.
Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
BLOCK (AAAI 2019), with a multimodal fusion library for deep learning models
HuggingSound: A toolkit for speech-related tasks based on Hugging Face's tools
A modular graph-based Retrieval-Augmented Generation (RAG) system
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
Vane is an AI-powered answering engine.
A game theoretic approach to explain the output of any machine learning model.
Schedule-Free Optimization in PyTorch
This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learna…