AI ओपन सोर्स प्रोजेक्ट

CodeGen

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

Mistral-Vibe (Mistral)

Minimal CLI coding agent by Mistral

Argilla

面向 AI 工程师与领域专家的数据标注与协作平台。

AIBrix

Cost-efficient and pluggable Infrastructure components for GenAI inference

AutoRAG

Your Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files.

ExecuTorch

On-device AI across mobile, embedded and edge for PyTorch

Text Embeddings Inference (Hugging Face)

A blazing fast inference solution for text embeddings models

Marqo

端到端的向量搜索引擎，内置嵌入生成。

AG2

AutoGen 社区延续版（AgentOS），面向开源多智能体系统。

PyTorch Forecasting

Time series forecasting with PyTorch

LangWatch

Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.

llm-d

Achieve state of the art inference performance with modern accelerators on Kubernetes

DJL (Deep Java Library)

An Engine-Agnostic Deep Learning Framework in Java

Agenta

Agenta is a workspace where you and your team build agents and automations.

Chonkie

🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

Macro

Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory.

PyTorch Ignite

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Seldon-core

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

Meta Lingua

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

DeskcommCRM

Open-source AI sales OS — self-hosted CRM with native AI agents + WhatsApp (WAHA). Open alternative to Kommo, Octadesk & Intercom for any business that sells by chat. MCP-ready, multi-tenant, LGPD.

linfa

A Rust machine learning framework.

Flux.jl

Relax! Flux is the ML library that doesn't make you tensor

Infinity (AI Database)

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

OB1

Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.