Applications LLM

Applications et frameworks LLM open source

C’est le groupe le plus large : interfaces de chat, SDK et frameworks, outils de prompts et d’évaluation, et applications reposant sur des grands modèles de langage. Beaucoup fonctionnent avec les modèles de plusieurs fournisseurs, et certains peuvent faire tourner des modèles sur votre propre matériel.

Comment choisir

Pour tout ce que vous comptez mettre en production, vérifiez d’abord trois faits : la licence, car certains projets populaires restreignent l’usage commercial ; la prise en charge du fournisseur de modèles que vous utilisez déjà ; et la maintenance du projet. L’encadré « En bref » de chaque page projet répond aux questions de licence et de maintenance à partir des données GitHub.

Projets les plus étoilés

433–456 sur 871

memodb-io

Acontext

★ 3 692

Agent Skills as a Memory Layer

JavaScript

Windy3f3f3f3f

how-claude-code-works

★ 3 636

Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码：架构、Agent 循环、上下文工程、工具系统等

nextlevelbuilder

goclaw

★ 3 603

GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.

sligter

LandPPT

★ 3 596

一个基于LLM的演示文稿生成平台，能够自动将文档内容转换为专业的PPT演示文稿。平台支持多种AI模型，提供丰富的模板和样式选择，让用户能够创建高质量的演示文稿。

Python

synthetic-sciences

openscience

★ 3 589

The open-source AI workbench for scientific research

TypeScript

deta

surf

★ 3 569

Personal AI Notebooks. Organize files & webpages and generate notes from them. Open source, local & open data, open model choice (incl. local).

TypeScript

NVlabs

Eagle

★ 3 568

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

Python

truera

trulens

★ 3 552

Évaluation et suivi des expériences LLM et des agents d'IA. Le traçage est natif d'OpenTelemetry, donc une trace est portable sur n'importe quel backend OTLP, et les évaluations s'exécutent soit au fur et à mesure que les traces atterrissent, soit sur un ensemble de données après coup.

Python

Open-Less

openless

★ 3 549

Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话，松开即得润色后的文字)

Rust

fnnx-ai

scikit-llm

★ 3 532

Seamlessly integrate LLMs into scikit-learn.

Python

SamurAIGPT

llm-wiki-agent

★ 3 527

A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.

Python

HanaokaYuzu

Gemini-API

★ 3 516

✨ Reverse-engineered Python API for Google Gemini web app

Python

aiming-lab

MetaClaw

★ 3 496

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

Python

FailproofAI

failproofai

★ 3 480

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan

MDX

DSXiangLi

DecryptPrompt

★ 3 440

总结Prompt&LLM论文，开源数据&模型，AIGC应用

modelscope

evalscope

★ 3 433

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

Python

Mesh-LLM

mesh-llm

★ 3 412

Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.

Rust

Leonxlnx

unlazy

★ 3 405

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

JavaScript

i-am-bee

beeai-framework

★ 3 401

Build production-ready AI agents in both Python and Typescript.

Python

Intelligent-Internet

ii-agent

★ 3 385

II-Agent: a new open-source framework to build and deploy intelligent agents

Python

HolmesGPT

holmesgpt

★ 3 384

SRE Agent - CNCF Sandbox Project

Python

simonlin1212

TradingAgents-astock

★ 3 353

A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。

Python

fuxicodex

Fuxi

★ 3 351

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.

Python

raiyanyahya

how-to-train-your-gpt

★ 3 343

Build a modern LLM from scratch. Every line commented. Explained like we are five.

Jupyter Notebook