Awesome Opensource Ai

Adding guardrails to large language models.

Flax is a neural network library for JAX that is designed for flexibility.

SkyReels-V2: Infinite-length Film Generative model

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

The Open Source Feature Store for AI/ML

Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows.

The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai

lightweight, standalone C++ inference engine for Google's Gemma models.

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

Fit interpretable models. Explain blackbox machine learning.

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

No description.

the portable Python dataframe library

Modeling, training, eval, and inference code for OLMo

可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Efficient Triton Kernels for LLM Training

TensorFlow documentation

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

Upserts, Deletes And Incremental Processing on Big Data.

A query and indexing engine for Redis, providing secondary indexing, full-text search, vector similarity search and aggregations.

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

A scikit-learn compatible neural network library that wraps PyTorch

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

FlashInfer: Kernel Library for LLM Serving

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

A system for quickly generating training data with weak supervision

Optimize prompts, code, and more with AI-powered Reflective Optimization

Open-source scientific and technical publishing system built on Pandoc.

An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.

A treasure chest for visual classification and recognition powered by PaddlePaddle

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

PyTorch native post-training library

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

Robust recipes to align language models with human and AI preferences

Gemma open-weight LLM library, from Google DeepMind

⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org

A PyTorch native platform for training generative AI models

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

Supercharge Your Model Training

CUDA accelerated rasterization of gaussian splatting

lakeFS - Data version control for your data lake | Git for data

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.