Awesome Opensource Ai

Fast, Flexible and Portable Structured Generation

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

OpenMLDB is an open-source machine learning database that provides a feature platform computing consistent features for training and inference.

Synthetic data curation for post-training and structured data extraction

Automated Machine Learning on Kubernetes

Manages Unified Access to Generative AI Services built on Envoy Gateway

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.

Scalable toolkit for efficient model reinforcement

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

An acausal modeling framework for automatically parallelized scientific machine learning (SciML) in Julia. A computer algebra system for integrated symbolics for physics-informed machine learning and automated transformations of differential equations

Apache Solr open-source search software

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

Machine learning with dataframes

Lightweight and extensible compatibility layer between dataframe libraries!

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

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

Reference implementations of MLPerf® inference benchmarks

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

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

Fast Multimodal LLM on Mobile Devices

A Data Streaming Library for Efficient Neural Network Training

Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

The LLM Anti-Framework

KaibanJS is a JavaScript-native framework for building and managing multi-agent systems with a Kanban-inspired approach.

Tools for building GPU clusters

Interface for OuteTTS models.

Agentic RL Training at Scale

Training Sparse Autoencoders on Language Models

Newelle - Your Ultimate Virtual Assistant

Scalable and memory-optimized training of diffusion models

Ground truth layer for humans and AI agents working together. Version control for knowledge.

An open source DevOps tool from the CNCF for packaging and versioning AI/ML models, datasets, code, and configuration into an OCI Artifact.

NASA Astrobee Robot Software

Humans and AI agents, building knowledge bases together. Self-hosted document annotation, version control, semantic search, and MCP.

bloom - evaluate any behavior immediately  🌸🌱

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

Code Editor for the AI Agents Era. Run multiple Claude Code and Codex agents across projects on your machine.

KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale

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

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.

XAI - An eXplainability toolbox for machine learning

Platform for AI-powered software engineers

🌎💪 BrowserGym, a Gym environment for web task automation

💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.

Scalable machine 🤖 learning for time series forecasting.

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

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

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.