Awesome Opensource Ai

The pretty much "official" DSPy framework for Typescript

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

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

Minimalistic large language model 3D-parallelism training

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

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.

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

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.

Data Contracts engine for the modern data stack. https://www.soda.io

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.

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

cuGraph - RAPIDS Graph Analytics Library

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

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

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

Agentic RL Training at Scale

Scalable toolkit for efficient model reinforcement

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

Fast, Flexible and Portable Structured Generation

Exploratory analysis of Bayesian models with Python

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

The good ol' Forge WebUI, now updated with new features~

Lightweight and extensible compatibility layer between dataframe libraries!

Automated Machine Learning on Kubernetes

MLRun is an open source MLOps platform for quickly building and managing continuous ML applications across their lifecycle. MLRun integrates into your development and CI/CD environment and automates the delivery of production data, ML pipelines, and online applications.

Draw datasets from within Python notebooks.

Machine learning with dataframes

A fast and lightweight framework for creating decentralized agents with ease.

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

Reference implementations of MLPerf® inference benchmarks

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Fast Multimodal LLM on Mobile Devices

🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

A Data Streaming Library for Efficient Neural Network Training

The official API server for Exllama. OAI compatible, lightweight, and fast.

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.

Scalable and memory-optimized training of diffusion models

🌎💪 BrowserGym, a Gym environment for web task automation

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.