AI ओपन सोर्स प्रोजेक्ट

rlm

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

OpenMed

Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK.

Alignment Handbook

Robust recipes to align language models with human and AI preferences

Agent Substrate

Agent Substrate: the core system

.NET Agent Skills

Repository for skills to assist AI coding agents with .NET and C#

ZenML

可移植、可复现的 MLOps 流水线框架。

TUIOS

A terminal window manager that knows what your agents are doing. Tiling panes, workspaces, sessions that survive restarts, and one Inbox for every coding agent.

Raven

The Harness of Harnesses • built for RSI: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

Composer

Supercharge Your Model Training

wigolo

The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.

RLinf

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

Agent Gateway

Next Generation Agentic Proxy for AI Agents and MCP servers

NVIDIA Model Optimizer

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment framew

DeepSeek-VL2

DeepSeek 的 MoE 视觉语言模型。

mini-sglang

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Peekaboo

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

hnswlib

HNSW 近似最近邻算法的 C++/Python 实现。

cuML

NVIDIA cuML: GPU-Accelerated Machine Learning

Code-Graph-RAG

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

GluonTS (AWS Labs)

Probabilistic time series modeling in Python

SynapseML

Simple and Distributed Machine Learning Python Library porting ML algorithms for Spark

XTuner

A Next-Generation Training Engine Built for Ultra-Large MoE Models

EasyR1

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

H2O LLM Studio

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/