llm

Dépôts LLM en tendance

IA & ML

Faire tourner, affiner et servir de grands modèles de langage.

Dépôts classés cette semaine
561
Activité par rapport à la semaine dernière
+78 %

Dépôts classés en LLM

40 sur 561 classés · étoiles gagnées cette semaine, rapportées à la taille · min. 20

Comment la santé est calculée
Rang 1

Reverse engineer anything with agents, from app behavior down to native binaries.

TypeScript298 kétoiles au total Santé : En bonne santéTypeScriptAgents IA
+230 k étoiles cette semaine
Rang 2

Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.

C2,9 kétoiles au total EmbarquéC & C++
+2,9 k étoiles cette semaine
Rang 4

基于 REA 深度拆解并高保真还原 Claude 官方桌面端 UI。还原 30 个独立 React 组件与 8 项硬核交互物理算法,附带 3000+ 行逆向分析手册。

TypeScript1,1 kétoiles au total Rétro-ingénierieUI & design systems
+1,1 k étoiles cette semaine
Rang 5

Autonomous AI sales agent powered by Claude Code or Codex. Finds prospects, writes cold emails, sends campaigns, handles replies, books meetings. No API keys needed — runs on your Claude or Codex subscriptions.

Python1,1 kétoiles au total Santé : En bonne santéClaude CodePython
+1 k étoiles cette semaine
Rang 7

Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository.

TypeScript919étoiles au total Tests & QATypeScript
+919 étoiles cette semaine
Rang 8

The operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent 的运维超集——完整继承 Pi 的核心能力,并进一步扩展可观测性、治理、故障恢复、评估和多 Agent 编排。

TypeScript1 kétoiles au total ObservabilitéMCP
+926 étoiles cette semaine
Rang 9

AI API 中转站评测排行与切换工具:实测可用率、延迟与价格 · Open-source AI API relay benchmark, rankings & switcher for Claude Code / Codex

Rust1,3 kétoiles au total Claude CodeApplis de bureau
+1,1 k étoiles cette semaine
Rang 10

Unlock Google 11's Gemini "Rambler" Natural Voice Dictation & AI Writing Tools on ANY Android phone. No root required.

Java936étoiles au total JavaAndroid
+810 étoiles cette semaine
Rang 11

Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya

Python763étoiles au total Claude CodeSkills d’agents
+694 étoiles cette semaine
Rang 12

Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.

Go14,5 kétoiles au total GoClaude Code
+6,3 k étoiles cette semaine
Rang 13

Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.

TypeScript837étoiles au total WindowsClaude Code
+703 étoiles cette semaine
Rang 14

Local-first AI teammate workspace. Bring your own models and keep project conversations, tool approvals, and results together.

TypeScript579étoiles au total Santé : En bonne santéLocal-firstMCP
+577 étoiles cette semaine
Rang 15

Open-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer.

Python3,9 kétoiles au total Auto-hébergéPython
+2,1 k étoiles cette semaine
Rang 16

AI-assisted RAW photo developer: GPT vision advisor proposes an EditRecipe, a deterministic Rust engine renders it — Lightroom-compatible XMP sidecars, 24 RAW formats + baked images, measured (not guessed) Lightroom mask geometry, local GUI/web UI, AI denoise & segmentation sidecars

Rust1,1 kétoiles au total Santé : En bonne santéVision par ordinateurRust
+818 étoiles cette semaine
Rang 17

CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.

Python847étoiles au total TerminalOutils CLI
+629 étoiles cette semaine
Rang 18

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式,带到每一个 AI 工具里。

Rust909étoiles au total Santé : En bonne santéSkills d’agentsApplis de bureau
+660 étoiles cette semaine
Rang 19

Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.

C++981étoiles au total LLM en localAuto-hébergé
+697 étoiles cette semaine
Rang 20

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C++445étoiles au total LLM en localmacOS
+372 étoiles cette semaine
Rang 21

Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.

Python370étoiles au total Vision par ordinateurPython
+370 étoiles cette semaine
Rang 23

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Go30,8 kétoiles au total Santé : En bonne santéSécuritéGo
+5,5 k étoiles cette semaine
Rang 24

DeepSeek Harness 破甲:让所有模型都能破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开,请查看署名要求部分

JavaScript6,5 kétoiles au total JavaScriptAgents de code
+2,2 k étoiles cette semaine
Rang 25

Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.

JavaScript334étoiles au total JavaScriptAgents de code
+334 étoiles cette semaine
Rang 27

☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.

Python308étoiles au total DomotiquePython
+305 étoiles cette semaine
Rang 28

Evolving Multimodal Inference Programs: LLM-guided evolutionary search for accurate and efficient vision-language inference.

Python332étoiles au total Python
+296 étoiles cette semaine
Rang 29

Claudemy: an open-source alternative to Udemy and Coursera. Give Claude a topic, it researches the web and builds a course of 2-minute audio lessons with cited sources. A free Claude Code skill.

Python291étoiles au total Claude CodePython
+291 étoiles cette semaine
Rang 30

A growing collection of viral videos made with Claude Opus 5.5 and the prompts behind them. Watch each original next to a live remake on Skillry. Updated regularly.

5,6 kétoiles au total
+1,8 k étoiles cette semaine
Rang 31

Describe any machine in one line. Claude builds a photoreal, physics based, interactive simulation of it in one HTML file, plus the film to post it. An open source Claude Code skill.

JavaScript286étoiles au total Skills d’agentsJavaScript
+286 étoiles cette semaine
Rang 32

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

TypeScript30,4 kétoiles au total Santé : En bonne santéMCPClaude Code
+4,2 k étoiles cette semaine
Rang 33

YouTube transcript skills for Claude Code, Cursor and Codex. Agent Skills to get transcripts, search YouTube, read channels and playlists, and bulk export.

271étoiles au total Skills d’agentsClaude Code
+256 étoiles cette semaine
Rang 34

Claude Code skill for short films with no video model: 51 film styles, each a style prompt plus a demo film made entirely in code by Claude Opus 5.5 (incl. OPUSCAR 98 and the new Evidence Films). By Lemomo. · Opus5.5 x 51 种影片风格:风格提示词 + 纯代码样片 + 导演与技术指南(新增「实证影像」)

JavaScript2,8 kétoiles au total Skills d’agentsJavaScript
+1 k étoiles cette semaine
Rang 36

Find the cheapest API for any model and connect it from your AI agent: Grandet Skill and an anonymous MCP server, backed by listed prices from 1,800+ official, inference and relay providers on grandet.ai.

JavaScript251étoiles au total Skills d’agentsMCP
+245 étoiles cette semaine
Rang 37

nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.

Swift1,4 kétoiles au total SwiftiOS
+640 étoiles cette semaine
Rang 38

Make Gemini code like Claude Models. Forces it to inspect files before editing, plan changes, test its work, and back up every “done” with actual evidence.

Python233étoiles au total Skills d’agentsPython
+221 étoiles cette semaine
Rang 39

Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.

C++1,1 kétoiles au total Santé : Signaux mitigésEmbarquéC & C++
+510 étoiles cette semaine
Rang 40

Claude Code, Codex, Copilot, Pi, OpenCode, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

JavaScript2,7 kétoiles au total Santé : En bonne santéSkills d’agentsJavaScript
+926 étoiles cette semaine