Awesome Opensource Ai

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

llama.cpp fork with additional SOTA quants and improved performance

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

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

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

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

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).

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

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.

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

A framework for prompt tuning using Intent-based Prompt Calibration

Inspect: A framework for large language model evaluations

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/

PyTorch native quantization for training and inference

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

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

Kubernetes-native Job Queueing

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

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS

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

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.

OpenLIT is the open-source agent harness engineering platform: trace, evaluate, guard, and improve everything around the model in your AI agents, on OTEL.

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

Minimalistic large language model 3D-parallelism training

Community maintained hardware plugin for vLLM on Ascend

An Open Standard for lineage metadata collection

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Machine learning metrics for distributed, scalable PyTorch applications.

SDG is a specialized framework designed to generate high-quality structured tabular data.

An AI-powered agentic red team framework that automates offensive security operations, from reconnaissance to exploitation to post-exploitation, with zero human intervention.

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

Bionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems.

Fully open data curation for reasoning models

A Python package to assess and improve fairness of machine learning models.

Feature engineering and selection open-source Python library compatible with sklearn.

Collect, aggregate, and visualize a data ecosystem's metadata

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

TFX is an end-to-end platform for deploying production ML pipelines

Helios: Real Real-Time Long Video Generation Model

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

Scalable toolkit for efficient model reinforcement