Awesome Opensource Ai

High-speed Large Language Model Serving for Local Deployment

Bayesian Modeling and Probabilistic Programming in Python

cuDF - GPU DataFrame Library

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

the LLM vulnerability scanner

Containers for machine learning

Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!

AutoML library for deep learning

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

🧙 Build, run, and manage data pipelines for integrating and transforming data.

Apache Beam is a unified programming model for Batch and Streaming data processing.

Build effective agents using Model Context Protocol and simple workflow patterns

OpenShell is the safe, private runtime for autonomous AI agents.

Out-of-Core hybrid Apache Arrow/NumPy DataFrame for Python, ML, visualization and exploration of big tabular data at a billion rows per second 🚀

Accessible large language models via k-bit quantization for PyTorch.

slime is an LLM post-training framework for RL Scaling.

FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models

[SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.

🧱 Easy fast local-first microVM runtime and library

A vector search SQLite extension that runs anywhere!

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

A Datacenter Scale Distributed Inference Serving Framework

Build autonomous AI agents in Python.

Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

Utilities intended for use with Llama models.

An open source python library for automated feature engineering

Adding guardrails to large language models.

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

Tools for merging pretrained large language models.

The Open Source Feature Store for AI/ML

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。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.

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

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

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

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

Fit interpretable models. Explain blackbox machine learning.

Modeling, training, eval, and inference code for OLMo

the portable Python dataframe library

Julep — durable, composable AI agents. Flows that crash and resume, retry safely, and explain every step.

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

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

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