Ultralight, security-first service mesh for Kubernetes. Main repo for Linkerd 2.x.

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Production-ready platform for agentic workflow development.

Distributed lock for your scheduled tasks

Backstage is an open framework for building developer portals

Open, Multi-modal Catalog for Data & AI

Streaming replication for SQLite.

Transactional schema-less embedded database used by JetBrains YouTrack and JetBrains Hub.

SOFABolt is a lightweight, easy to use and high performance remoting framework based on Netty.

Java implementation of RSocket

QuestDB is a high performance, open-source, time-series database

FoundationDB - the open source, distributed, transactional key-value store

Skupper is an implementation of a Virtual Application Network, enabling rich hybrid cloud communication.

📊 Cube Core is open-source semantic layer and LookML alternative for AI, BI and embedded analytics

StAEDI - Streaming API for EDI: Java library featuring a reader/parser, writer/generator, and validation

A mock implementation of the AWS S3 API startable as Docker image, TestContainer, JUnit 4 rule, JUnit Jupiter extension or TestNG listener

COPPER - a high performance Java workflow engine

A library that provides an embeddable, persistent key-value store for fast storage.

A Unified Library for Parameter-Efficient and Modular Transfer Learning

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

An extremely easy way to perform background processing in Java. Backed by persistent storage. Open and free for commercial use.

Yi-1.5 is an upgraded version of Yi, delivering stronger performance in coding, math, reasoning, and instruction-following capability.

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.