Trending AI GitHub Repos This Week (2026-10-21)
New AI repositories (LLM, AI agents, MCP, RAG, generative AI) created in the last 30 days and active in the last 7, ranked by GitHub stars.
Source: GitHub REST API repository search · Data checked on 2026-10-21 · Machine-readable JSON
| Rank | Repo | Stars | Stars gained | Intro (repo description) | Language | Created | License |
|---|---|---|---|---|---|---|---|
| 1 | Ebony-Vinyl/dsh-our-free-model | 33,238 | n/a (first snapshot) | 在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap. | JavaScript | 2026-09-24 | MIT |
| 2 | yetone/magpie | 18,696 | n/a (first snapshot) | Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar. | Go | 2026-09-23 | MIT |
| 3 | tangency-labs/solidcraft | 8,686 | n/a (first snapshot) | SolidCraft: an open-source parametric 3D CAD application built in pure Rust. Desktop, web, and automation through MCP. | Rust | 2026-10-07 | Apache-2.0 |
| 4 | rehan-remade/universal-modder | 8,610 | n/a (first snapshot) | Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos. | Python | 2026-09-30 | MIT |
| 5 | KKKKhazix/AIHOT | 8,343 | n/a (first snapshot) | 一个自己找热点、自己写日报的网站框架。把信源和精选标准换成你的，它就是你的行业热点站。 | TypeScript | 2026-09-28 | MIT |
| 6 | jev-chat/jev-chat-jarvis | 7,961 | n/a (first snapshot) | The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill in with one tap. You press send. Android · Windows · macOS · iOS | 聊天辅助决策工具：先看懂对方再回复，发不发由你。 | Kotlin | 2026-09-21 | MIT |
| 7 | Louis-CFM/coucou | 5,677 | n/a (first snapshot) | A tiny friend in your Mac's notch and on your iPhone that keeps an eye on your AI coding agents: Claude Code, Codex, Cursor, Gemini CLI, Antigravity and more. Approve from the notch or your Lock Screen. | Swift | 2026-09-27 | MIT |
| 8 | lemomo-ai/lemo-opuscar | 4,772 | n/a (first snapshot) | 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」） | JavaScript | 2026-09-26 | MIT |
| 9 | QingYunA/answer-me-with-html | 4,163 | n/a (first snapshot) | Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。 | JavaScript | 2026-10-02 | MIT |
| 10 | onehumanbeing/esp32-iphone-agent | 3,466 | n/a (first snapshot) | 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. | C | 2026-10-11 | MIT |
| 11 | nanaism/yomiyasu | 2,378 | n/a (first snapshot) | AI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese | Python | 2026-09-30 | MIT |
| 12 | Folkbench/folkbench | 2,234 | n/a (first snapshot) | 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 | Rust | 2026-10-02 | Other |
| 13 | deeplethe/solid-glass | 2,098 | n/a (first snapshot) | A design system for AI applications. Material, physical, tactile, technical. | TypeScript | 2026-10-12 | MIT |
| 14 | nano-muse/nanoMuse | 2,092 | n/a (first snapshot) | 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. | Swift | 2026-09-23 | GPL-3.0 |
| 15 | Leonxlnx/earshot | 2,036 | n/a (first snapshot) | Ears for coding agents: let AI hear, review and make sound. CPU-only, open source. | Python | 2026-10-15 | MIT |
| 16 | amontlabs/lcu | 2,024 | n/a (first snapshot) | Codex computer use, decoupled from the app, for usage inside any harness. | JavaScript | 2026-09-22 | MIT |
| 17 | jiwoochris/artex-global | 1,892 | n/a (first snapshot) | ARTEX 한국어판 · AI 자율 침투 테스트 프레임워크(upstream: Autumn-27/ARTEX, AGPL-3.0) | Go | 2026-10-03 | AGPL-3.0 |
| 18 | zhuyansen/new-term-radar | 1,600 | n/a (first snapshot) | Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them. | Python | 2026-10-12 | MIT |
| 19 | freestylefly/WeChatBridge | 1,554 | n/a (first snapshot) | 微信聊天记录一键转发到 AI Agent 与 Obsidian 的原生 macOS 工具 | Swift | 2026-09-21 | MIT |
| 20 | trhhubsd/ARTEX | 1,543 | n/a (first snapshot) | ARTEX · AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) · AI 自主渗透测试系统 · 百度 agent+ 攻防挑战赛冠军 | Go | 2026-10-08 | AGPL-3.0 |
| 21 | rociiu/talorys | 1,363 | n/a (first snapshot) | Your personal AI agent in your own Cloudflare account. Chat, memory, tasks, notes and scheduled reminders, deployed with one command: npx create-talorys@latest. Free-tier friendly, single-user, no telemetry. | TypeScript | 2026-10-10 | MIT |
| 22 | mw00/project-maya | 1,361 | n/a (first snapshot) | Project Maya - run GLM-5.3-Flash (321B MoE) and DeepSeek-V4.1-Flash-1017 (748B 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++ | 2026-10-06 | MIT |
| 23 | marclou/mailcheap | 1,282 | n/a (first snapshot) | Newsletters where you pay for the emails you send, not for dormant subscribers, at a fraction of the price of beehiiv and the like. Open source: self-host it, or use mailcheap.ai. | JavaScript | 2026-10-10 | AGPL-3.0 |
| 24 | jwuthri-cloud/Tracely-ai | 1,162 | n/a (first snapshot) | Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them into replayable regression tests, and block PRs that regress. Self-hostable. | Python | 2026-10-11 | MIT |
| 25 | StartLuxLabs/StartLux-Decision | 1,094 | n/a (first snapshot) | Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX. | Python | 2026-09-29 | Apache-2.0 |
| 26 | morluto/awesome-reverse-engineering | 1,048 | n/a (first snapshot) | Curated reverse-engineering tools and learning resources for binaries, apps, firmware, formats, and protocols. | Python | 2026-10-09 | CC0-1.0 |
| 27 | Harvil1/codeAgent | 1,026 | n/a (first snapshot) | 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. | Python | 2026-10-02 | MIT |
| 28 | Edwardxlai/easyread | 997 | n/a (first snapshot) | 把英文论文读成舒服的中文：本地 PDF 论文翻译、原文对照、边读边问 AI、文献管理。Read English papers in comfortable Chinese. | Python | 2026-09-30 | MIT |
| 29 | LiCinCan/blender-ai-mcp-addon | 965 | n/a (first snapshot) | AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with OpenAI, ChatGPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon and plugin, copilot for 3D, bpy Python scripting, MCP integration. | Python | 2026-10-15 | MIT |
| 30 | GanyuanRan/Autoloom | 961 | n/a (first snapshot) | AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发执行，让变更有依据、交付有证据。用创意编织现实。 | JavaScript | 2026-09-30 | Other |
Methodology
GitHub search for topics llm, ai-agent, ai-agents, mcp, generative-ai, large-language-models, agentic-ai, rag; repos created on/after 2026-09-21, pushed on/after 2026-10-14, not forks or archived; merged and sorted by total stars (top 30). "Stars gained" compares with our previous saved snapshot (none yet — gains appear from the next refresh). Stars measure attention, not quality; descriptions are the repos' own.
Get the 5 best new AI tools every week
One short email every Friday. No spam, unsubscribe anytime.