AI 頻道
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 673–696 個,共 866 個
1,702

Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.

TypeScript
kubeflow

katib

1,701

Automated Machine Learning on Kubernetes

Python
kwaroran

Risuai

1,681

Make your own story. User-friendly software for LLM roleplaying

TypeScript
lotus-data

lotus

1,681

Optimized Agentic and LLM Bulk Processing Over Your Data

Python
SemiAnalysisAI

InferenceX

1,676

開源連續推理基準研究平台、Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 以及即將推出的 TPUv6e/v7/Trainium2/300505,005 代碼NVL72 vs MI355X vs B200 vs GB300 NVL72 TPUv6e/v7/Trainium2/3。

Python
gi-dellav

zerostack

1,673

Lightweight coding agent written in Rust, optimized for memory footprint and performance

Rust
tenstorrent

tt-metal

1,673

TT-NN 運算子庫和 TT-Metaium 低階內核程式設計模型。

C++
intentee

paddler

1,672

Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

Rust
Gitlawb

zero

1,671

編碼代理可以回答您、您的模型、您的機器、您的規則。

Go
AgentR1

Agent-R1

1,669

Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

Python
PurpleDoubleD

locally-uncensored

1,667

The all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required.

TypeScript
FrigadeHQ

trench

1,663

Trench — Open-Source Analytics Infrastructure. A single production-ready Docker image built on ClickHouse, Kafka, and Node.js for tracking events. Easily build product analytics dashboards, LLM RAGs, observability platforms, or any other analytics product.

TypeScript
legeling

PromptHub

1,653

一款包含了 Prompt管理,Skill管理,Agent管理的一站式AI工具箱,助你高效管理提示词,一键分发skills ,一站式管理Agent资产,并实现云同步,备份,版本管理 | An all-in-one AI toolbox for prompt, agent, and skills management. Reuse prompts, distribute skills with one click, manage agent assets, and support cloud sync, backup, and version control

TypeScript
Tencent

AngelSlim

1,651

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

Python
patoles

agent-flow

1,647

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

TypeScript
theopenco

llmgateway

1,641

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

TypeScript
mediar-ai

terminator

1,639

playwright for windows computer use

Rust
fetchai

uAgents

1,636

A fast and lightweight framework for creating decentralized agents with ease.

Python
psalias2006

gpu-hot

1,636

🔥 Real-time NVIDIA GPU dashboard

JavaScript
1,629

Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

JavaScript
Darkatse

TauriTavern

1,624

The classic Sillytavern, now has been rewritten in Tauri/Rust.

JavaScript
1,624

This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.

Jupyter Notebook
pixeltable

pixeltable

1,623

The unified multimodal backend for AI data apps. Database, orchestration, and serving in one Python file.

Python
lucasastorian

llmwiki

1,615

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

Python