Stars
Production-ready platform for agentic workflow development.
A modern runtime for JavaScript and TypeScript.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
The fastest path to AI-powered full stack observability, even for lean teams.
Free and Open Source, Distributed, RESTful Search Engine
Apache Superset is a Data Visualization and Data Exploration Platform
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
LlamaIndex is the leading framework for building LLM-powered agents over your data.
The easy-to-use open source Business Intelligence and Embedded Analytics tool that lets everyone work with data 📊
Official Code for DragGAN (SIGGRAPH 2023)
High performance Node.js image processing, the fastest module to resize JPEG, PNG, WebP, AVIF and TIFF images. Uses the libvips library.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
GUI for a Vocal Remover that uses Deep Neural Networks.
x86 PC emulator and x86-to-wasm JIT, running in the browser
QuestDB is a high performance, open-source, time-series database
Embeddable Postgres with real-time, reactive bindings.
💡 All-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows
Sentry, feature-complete and packaged up for low-volume deployments and proofs-of-concept
Pythonic AI generation of images and videos
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
The transactional Elasticsearch alternative built on Postgres
A multi window layout manager for webapps
AirLLM 70B inference with single 4GB GPU