Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

• UpdatedFeb 20, 2026
• Go

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

• UpdatedFeb 20, 2026
• Python

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

• UpdatedFeb 19, 2026
• JavaScript

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

• UpdatedFeb 19, 2026
• Python

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

• UpdatedJan 6, 2026
• Python

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

• UpdatedFeb 10, 2026
• Jupyter Notebook

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

• UpdatedFeb 19, 2026
• Python

LLM agents built for control. Designed for real-world use. Deployed in minutes.

• UpdatedFeb 19, 2026
• Python

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

• UpdatedFeb 20, 2026
• Python

Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.

• UpdatedFeb 20, 2026
• Kotlin

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

• UpdatedFeb 13, 2026
• Python

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

• UpdatedFeb 14, 2026
• Python

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

• UpdatedOct 24, 2024
• Python

Efficient Triton Kernels for LLM Training

• UpdatedFeb 20, 2026
• Python

Chat with your notes & see links to related content with AI embeddings. Use local models or 100+ via APIs like Claude, Gemini, ChatGPT & Llama 3

• UpdatedFeb 12, 2026
• JavaScript

A python module to repair invalid JSON from LLMs

• UpdatedFeb 17, 2026
• Python

Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。

• UpdatedJan 6, 2026
• Python

A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.

• UpdatedFeb 17, 2026
• C#

Devon: An open-source pair programmer

• UpdatedMay 26, 2025
• Python

An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.

• UpdatedOct 21, 2024
• Python