AI ओपन सोर्स प्रोजेक्ट

Chronos (Amazon)

Chronos: Pretrained Models for Time Series Forecasting

KServe

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

Agents CLI (Google)

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

Higgsfield

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

SWE-bench

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Webwright

A simple SWE-style browser+desktop agent framework that achieves SOTA results on long-horizon CUA tasks

llama-swap

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

Volcano

A Cloud Native Batch System (Project under CNCF)

Snorkel

A system for quickly generating training data with weak supervision

shimmy

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

Paperless-AI

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.

LLocalSearch

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the

Giskard

🐢 Open-Source Evaluation & Testing library for LLM Agents

AgentOps

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

rLLM

Democratizing Reinforcement Learning for LLMs

GPUStack

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

Maka

Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.

TorchTitan (PyTorch)

A PyTorch native platform for training generative AI models

torchtune

PyTorch 原生的大模型后训练库。

Gemma

Google DeepMind 的 Gemma 开放模型库，含推理与微调示例。

NVIDIA DALI

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

UltraRAG (OpenBMB)

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

Captum

Model interpretability and understanding for PyTorch

Casibase

⚡️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