SWIFT (Scalable lightWeight Infrastructure for Fine-Tuning) is an extensible framwork designed to facilitate lightweight model fine-tuning.

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

ModelScope: bring the notion of Model-as-a-Service to life.

A high-throughput and memory-efficient inference and serving engine for LLMs

PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker

🙌 OpenHands: Code Less, Make More

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Agent computer interface for AI software engineer.

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

CLI platform to experiment with codegen. Precursor to: https://lovable.dev

LLM inference in C/C++

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

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 yo…

TEN Agent is a conversational AI powered by TEN, integrating Gemini 2.0 Multimodal Live API, OpenAI Realtime API, RTC, and more. It offers real-time capabilities to see, hear, and speak, along with…

The open-source repo for docs.dify.ai

OpenMMLab Computer Vision Foundation

Efficient Triton Kernels for LLM Training

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

Llama3 中文仓库（聚合资料：各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、部署教程视频 & 文档）

FaceChain is a deep-learning toolchain for generating your Digital-Twin.