Open-source multimodal retrieval engine (Morphik Core)
- artificial-intelligence
- cache-augmented-generation
- colpali
- database
77,852 visible repositories in the index
217–240 of 720 · Most stars
Open-source multimodal retrieval engine (Morphik Core)
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
Evaluation and Tracking for LLM Experiments and AI Agents
Apache Lucene open-source search software
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
SIMD, SWAR & GPU kernels for strings: search, hashing, sorting, edit distances, UTF-8 segmentation & ciphers for C, C++, CUDA, Python, Rust, Go, Swift, JS, C# & Java 🦖
Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.
GitHub has sold us out. Time to get out.
[NeurIPS 2026] DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
💉 ReVanced Patcher used to patch Android applications
[KDD'2026] "VideoRAG: Chat with Your Videos"
Open-source inference server and production cluster for all the models your agent needs.
MTEB: State-of-the-art evaluation of embeddings across languages and modalities
Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier
Laminar - open-source observability platform purpose-built for AI agents. YC S24.
An image effects library for JavaScript using WebGL
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Code for the paper "Evaluating Large Language Models Trained on Code"
OpenSource Claude Cowork. A desktop AI assistant that helps you with programming, file management, and any task you can describe.
Accelerated deep learning R&D
A library for audio and music analysis, feature extraction.
An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.
This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction
Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.