AI開発影響研究所 EN
← 月別アーカイブ · SNAPSHOT 2026-06
月次スナップショット

2026年6月 のAI開発状況

2026年6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。

851
観測したAI関連Repo
94
個人開発候補
105
Web公開候補
248
AIツール痕跡

※ 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)

8.9%
AIで作られたRepo ±1.3pt · AIを使うRepo 4.4% · いずれか 12.2%

2026-06 のアクティブRepoから無作為抽出した 1,773 件を判定した結果です。 カッコ内は95%信頼区間の幅。 GitHub全体(11,753,398 Repo)に当てはめると 約 1,040,769 Repo に相当します。 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)

176,182,181
累計Repo
+4.7% 前月比
11,753,398
アクティブRepo
+0.1% 前月比
10,040,434
作成イベント
-4.9% 前月比
68,905
fork
5,039,271
新規公開Repo
+1.2% 前月比
95,398,281
pushイベント
+7.6% 前月比
310,744
star/watch

※ fork / star・watch は 2025年後半以降 GH Archive 側の記録が大幅に欠落しています。値はそのまま載せていますが、前月比は算出していません。

REPOS 2026年6月 のTOP20 Repo

ray-r-ren/agent-apprenticeship

The 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.

Python 595 AI 100
gameworkerkim/cassandra-ai

코스닥 DART 공시 실시간 분석 + 섹터 공포·탐욕 지수 + 사주 기반 종목 궁합 + 페르소나 투자 AI. Supabase·Neon·Redis·Vercel $0/월 인프라. Google 로그인으로 무료 이용.

TypeScript 41 AI 50
IssacW228/student-llm-wiki

📚 Student LLM Wiki — AI-compiled knowledge base for university students. Drop course slides, get a persistent interlinked wiki. Feynman review, exam prep, confidence decay, cross-course connections. Based on Karpathy's LLM Wiki pattern. Works with Claude Cowork / Claude Code / Claudian + Obsidian.学生大语言模型维基百科——专为大学生打造的AI编译知识库。

33 AI 100 3 sig
dujunyi416/claude-nightshift

Quota-aware automation for Claude Code: check rate limits, pre-warm the 5h window before you wake, queue prompts overnight, auto-resume interrupted sessions on reset.

Python 26 AI 75
richchang0721-boop/it-diagnostic-agent

互動式 IT 故障排除 Runbook,整合 Claude AI。涵蓋 CCTV、NAS、AD、Exchange、Outlook 等企業常見場景。純靜態 HTML,GitHub Pages 一鍵部署。AI-powered IT troubleshooting runbook for Active Directory, Exchange, Outlook, NAS, CCTV and manufacturing environments. Designed for real-world IT operations and support teams.

HTML 18 AI 90
nnguyenquangg/claude-code-spec-driven-development
Shell 18 AI 50
SuperJayLiu/AI-for-Economics-and-Finance-Research

An "all-you-need-to-know" practical guide to using AI and LLMs responsibly and effectively for economics and finance research: from core skills and ChatGPT/Claude Projects to coding, writing, reproducibility, and automation. 小红书账号:SuperJay

HTML 14 AI 100
RiggdAI/uniqent

Any brain, any agent. Package an AI agent's brain — persona, MCP stack, skills, memory, config — into one open, signed bundle and install it into any framework (OpenClaw, Hermes, Claude Code) in one click.

TypeScript 14 AI 70 1 sig
su5176/Mklink-AI-Probe

MKLink AI Probe is an all-in-one embedded debugging CLI for Cortex-M microcontrollers. It bridges the MKLink/MicroLink hardware probe with AI agents (Claude, OpenAI) to enable natural-language driven firmware flashing, real-time waveform visualization, memory inspection, fault diagnosis, and industrial protocol debugging.

Python 11 AI 65
KorroAi/korrodesign

Design enforcement system, not a code generator. Two independent layers (Taste Guardian + Blind Spot ESLint). 7-phase design pipeline. Zero runtime dependencies. Awwwards-level output.

JavaScript 10 AI 45
mythkiven/rednote-director-skill

面向小红书/RedNote 创作者的 Agent Skill:图文轮播规划、视觉导演、封面内页设计、AI 生图提示词与发布文案。支持 Cursor、Claude、Codex。

9 AI 70 1 sig
hoangpm96/ai-switcher

A native macOS app to manage and switch between multiple accounts for AI coding tools — Claude Code, Codex, and Antigravity IDE — from one place.

Rust 7 AI 75 1 sig
DYAI2025/Plumbline

Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. 87 subagents + skills, TDD defense-in-depth gates, Kaizen retros, a four-body adversarial council, and an empirically benchmarked QA harness. Does it hang true?

Shell 6 AI 70 1 sig
JordanDalton/laravel-tackle

Tackle is the runtime layer that lets AI agents operate inside your Laravel application — reading code, executing tools, running tests, and taking action, with safety boundaries enforced at the framework level.

PHP 6 AI 45
SuvenSeo/ai-coding-usage-tracker

Local-first AI coding usage dashboard for Codex, Claude Code, and Cursor — tokens, credits, USD estimates, native GUI, and WakaTime sync.

Python 5 AI 100
Doulor/Clawd-Companion

Claude Code 桌宠伴侣 — 透明桌宠窗口实时显示 Claude Code 的工具调用、会话状态和完成提醒。

TypeScript 5 AI 45 2 sig
jianshuo/cchour

See how much time you spend in AI coding tools (Claude Code / Codex) — local HTML report from session logs

JavaScript 5 AI 45 1 sig
cshotwe/odd

Outcome-Driven Development for coding agents — declare the outcome, prove it against the real artifact, review the diff like a maintainer.

Python 5 AI 45
tashfeenahmed/AgentDomains-skill

Claude/agent skill for AgentDNS — free *.makes.fyi subdomains for AI agents

Shell 4 AI 75
Kerlewor/narrative_workbench

面向 Claude Code 与 Codex CLI 的 AI 小说写作工程框架 | Inspired by InkOS | AGPL-3.0

Python 4 AI 70 2 sig

EXPLORE 関連ページ

📝

月次レポート

この月の動向を分析したレポートを探す

📊

13ランキング

採用率カテゴリ別ランキング

📅

他の月も見る

月次アーカイブ全件