HZF316

SwanLab

⚡️SwanLab: your ML experiment notebook. 你的AI实验笔记本，跟踪与可视化你的机器学习全流程

koupleless

modular dev framework and serving platform to enable app evolve from monolithic to microservices and also serverless smoothly. 模块化研发框架与运维调度系统，帮助应用解决研发运维系列痛点问题，省资源、秒级启动、灵活部署、快速需求交付等

LWM

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

lm-evaluation-harness

A framework for few-shot evaluation of language models.

llm.c

LLM training in simple, raw C/CUDA

llama-cpp-python

Python bindings for llama.cpp

llama.cpp

LLM inference in C/C++

llama3-chinese

Llama3-Chinese是以Meta-Llama-3-8B为底座，使用 DORA + LORA+ 的训练方法，在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。

proxy_pool

Python ProxyPool for web spider

awesome-spider

爬虫集合

llama3

The official Meta Llama 3 GitHub site

langgraph

Build resilient language agents as graphs.

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

XAgent

An Autonomous LLM Agent for Complex Task Solving

lobe-chat

🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Azure / DeepSeek), Knowledge Base (file upload / knowledge management / RAG ), Multi-Modals (Vision/TTS) and plugin system. One-click FREE deployment of your private ChatGPT/ Claude application.

pnpm

Fast, disk space efficient package manager

openllmetry

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

mona-openai

ai-getting-started

A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs

mem0

The Memory layer for your AI apps

langchain-gradio-template

langchain-streamlit-template

LangChain.js-LLM-Template

This is a LangChain LLM template that allows you to train your own custom AI LLM.

create-t3-turbo-ai

Build full-stack, type-safe, LLM-powered apps with the T3 Stack, Turborepo, OpenAI, and Langchain

ai

Build AI-powered applications with React, Svelte, Vue, and Solid

Qwen-Agent

Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

MetaGPT

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

chat-langchain