2026年10月 のAI開発状況
2026年10月時点でGitHub上に観測されたAI関連リポジトリの数値スナップショット。AI関連Repo数・個人開発候補・Web公開候補・AIツール痕跡数を、GH ArchiveのGitHub全体イベント数と並べて見ます。
※ これらは当サイトがその月に観測できた件数です。GitHub全体の件数ではありません。収集量に左右されるため、月をまたいだ増減は動向を意味しません。全体に対する比率は下の「標本調査」をご覧ください。
SAMPLE AI開発の比率 (標本調査)
2026-10 のアクティブRepoから無作為抽出した 1,736 件を判定した結果です。 カッコ内は95%信頼区間の幅。 この月は GH Archive のイベント取り込みに欠落があるため、 実数への換算は掲載していません(比率は標本から直接測っているので影響を受けません)。 比率は当サイトの収集量に左右されないため、収集が遅れた月でも数値は歪みません。
CONTEXT GitHub全体の活動量 (GH Archive)
※ この月は GH Archive のイベント取り込み自体に欠落があります(日次のイベント数が同じ月の中で最大7倍ちがいます)。値は取得できたぶんをそのまま載せていますが、他の月と比較できる数ではないため前月比は算出していません。
REPOS 2026年10月 のTOP20 Repo
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.
lexmount/moliBest headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust
experientiallabs/experientialExperiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.
open-slide/open-slideA slide framework built for agents.
CopilotKit/OpenBotOpen-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
WenyuChiou/awesome-agentic-ai-zhA trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。
AminBlg/SimpleEnglishAgent skill: make LLMs write docs in ASD-STE100 Simplified Technical
plannotator/effective-htmlAgent skills for useful HTML artifacts, wireframes, interactive prototypes, plans, and diagrams.
Sophomoresty/gemini-web2apiConvert Google Gemini web into OpenAI-compatible API. Zero auth, cross-platform, single file.
Javis603/token-monitorLocal-first desktop widget for tracking token usage, costs, limits, and session activity across 47+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, OpenClaw, and more—with multi-device sync.
HarnessRouter/harnessrouterHarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
dzhng/jevgrepFind code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.
Alisa0808/vox-directorTurn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
ithtelab/workbuddy-manager腾讯 CodeBuddy 账号池管理控制台,内置 OpenAI 兼容反代网关:扫码批量纳管账号、定时签到与保活、密钥分组分发、IP 与模型白名单、调用日志与用量统计;支持带签名校验的一键更新。
cbrock84/headcountAn agent organization structured as a company — 15+ departments, 125+ skills, each independently installable, citing the standards and regulators that settle the question. Runs in Claude Code and ChatGPT.
Doorman11991/smallcodeAI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.
coji/natural-japanese仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。
Eynzof/Hermes-CN-DesktopHermes Agent CN desktop app, Windows-First, built with Tauri, Typescript and Rust. Isolated Hermes Agent core insides.
ray-r-ren/agent-apprenticeshipThe living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
uzairansaruzi/hermexNative iPhone app for your Hermes agent