Skip to content
BetaAI and tech news.Edition of Fri 16 Oct 2026 

AI repos on 15 Oct 2026

The list as it stood that day: new AI repositories on GitHub (created in the 30 days before) that gained the most stars.

Updated 15 Oct 2026, 16:16 UTCSource: GitHub REST API
#RepositoryDescriptionLanguageStars
01magpieyetoneEvery agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.Go13,370
02laya-mlxmizorewwwNative MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.Python6,941
03coucouLouis-CFMA 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.Swift5,283
04answer-me-with-htmlQingYunAAnswer 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。JavaScript3,440
05aurelio-financeLosaLosSantosOpen-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer.Python3,384
06reelmimicedenfunfShow it a video you love. Get a new video in the same style. An AI crew (Claude Code or Codex) plans, builds and reviews it with you.JavaScript3,318
07geo-sleuthOldcircleAn agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.Python2,949
08awesome-jevyibieA curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.Python2,352
09esp32-iphone-agentonehumanbeingLet 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.C2,336
10inkloomInkloom-artSpecialised AI models for logo design — a brand-analysis model turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces real lockups and clear-space rules. Early access open.TypeScript1,791
11herdr-gpuipensoNative client for Herdr on macOS, Linux, and Windows, built with Rust and GPUI. View terminal sessions, workspaces, Git worktrees, and agent activity through your local Herdr daemon.Rust1,396
12golive-skillmikehasaTake your agent-built product live: hosting, database, domain, email, payments — on your own accounts. Open-source Agent Skill + zero-dependency Node CLI: detect → plan → approve → apply → verify. No GoLive account, backend or telemetry.TypeScript1,284
13AnyJevnokia-applied-researchTurn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)Python1,276
14nanoMusenano-musenanoMuse: 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.Swift1,254
15typesafe-computer-useawlevinComputer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.Python1,234
16topconf-paper-figure-galleryqwdwqfwq3,516 curated Figure 1 / teasers from ICLR, ICML, NeurIPS, CVPR, ACL, AAAI (2023-2026), with tier badges and FigureForge retrieval-augmented figure draftingHTML977
17mailcheapmarclouNewsletters 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.JavaScript969
18solid-glassdeepletheA design system for AI applications. Material, physical, tactile, technical.TypeScript953
19vonwfzyxThe open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.Python906
20project-mayamw00Project 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++891

Star growth appears after the second snapshot.