大型語言模型應用

開源大型語言模型應用與框架

這是範圍最廣的一組：聊天介面、SDK 與框架、提示詞與評測工具，以及各種以大型語言模型為基礎的應用。很多專案可以接入多家服務商的模型，有些還能在你自己的硬體上執行模型。

怎麼選

打算用在產品裡的話，先確認三件事：授權——有些熱門專案限制商用；是否支援你正在用的模型服務商；以及它是否還在維護。每個專案頁上的「秒懂」卡片會根據 GitHub 資料回答授權和維護這兩個問題。

星數最多的專案

第 697–720 個，共 866 個

intel

auto-round

★ 1,614

英特爾 AutoRound 是一款用於量化工作流程的模型最佳化工具包，可降低推理成本，同時保持人工智慧部署的準確性。

Python

UbiquitousLearning

mllm

★ 1,612

Fast Multimodal LLM on Mobile Devices

C++

MLGroupJLU

LLM-eval-survey

★ 1,611

The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".

koreainvestment

open-trading-api

★ 1,606

Korea Investment & Securities Open API Github

Python

shiwenwen

hope-agent

★ 1,603

🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手，也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deployment

Rust

MeetKai

functionary

★ 1,596

Chat language model that can use tools and interpret the results

Python

Kaelio

ktx

★ 1,593

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company

TypeScript

OpenOSINT

★ 1,590

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

Python

mex-memory

mex

★ 1,585

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

TypeScript

AIScientists-Dev

academic-humanizer

★ 1,580

Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying claims to evidence. A skill for Claude Code, Codex, and MorphMind.

BAI-LAB

MemoryOS

★ 1,579

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

Python

openedclaude

claude-reviews-claude

★ 1,577

Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.

WeiboAI

VibeThinker

★ 1,577

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

Python

waybarrios

vllm-mlx

★ 1,575

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

Python

MLSysOps

🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Gemini, Ollama, etc supported. :fireworks: Code RAG

Python