Awesome Opensource Ai

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

II-Agent: a new open-source framework to build and deploy intelligent agents

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Build production-ready AI agents in both Python and Typescript.

JAX-based neural network library

🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Dead simple FLUX LoRA training UI with LOW VRAM support

Scalable and efficient data transformation framework - backwards compatible with dbt.

The Security Toolkit for LLM Interactions

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

OneTrainer is a one-stop solution for all your Diffusion training needs.

Visualize and compare datasets, target values and associations, with one line of code.

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app.

Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed.

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).

🦜💬 Web app for interacting with any LangGraph agent (PY & TS) via a chat interface.

An open-source visual programming environment for battle-testing prompts to LLMs.

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

A framework for prompt tuning using Intent-based Prompt Calibration

llama.cpp fork with additional SOTA quants and improved performance

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

Deepnote is a drop-in replacement for Jupyter with an AI-first design, sleek UI, new blocks, and native data integrations. Use Python, R, and SQL locally in your favorite IDE, then scale to Deepnote cloud for real-time collaboration, Deepnote agent, and deployable data apps. https://deepnote.com/

pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

PyTorch native quantization for training and inference

Stateful agents that are like people, with memory, identity, and the ability to learn and adapt

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Data manipulation and transformation for audio signal processing, powered by PyTorch

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.

The pretty much "official" DSPy framework for Typescript

The hub for EleutherAI's work on interpretability and learning dynamics

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

Multi-framework streaming Markdown renderers for AI apps: Vue/Nuxt, React/Next.js, Svelte, and Angular, with Mermaid, KaTeX, Shiki, Monaco, safe HTML, and low-jitter updates.

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

Ruler — apply the same rules to all coding agents

A library for debugging/inspecting machine learning classifiers and explaining their predictions

Minimalistic large language model 3D-parallelism training

Kubernetes-native Job Queueing

Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.