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。
※ 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)
2026-06 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)
※ 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
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.
gameworkerkim/cassandra-ai코스닥 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.
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。
dujunyi416/claude-nightshiftQuota-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.
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.
nnguyenquangg/claude-code-spec-driven-development SuperJayLiu/AI-for-Economics-and-Finance-ResearchAn "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
RiggdAI/uniqentAny 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.
su5176/Mklink-AI-ProbeMKLink 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.
KorroAi/korrodesignDesign enforcement system, not a code generator. Two independent layers (Taste Guardian + Blind Spot ESLint). 7-phase design pipeline. Zero runtime dependencies. Awwwards-level output.
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。
hoangpm96/ai-switcherA native macOS app to manage and switch between multiple accounts for AI coding tools — Claude Code, Codex, and Antigravity IDE — from one place.
DYAI2025/PlumblinePlumbline — 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?
JordanDalton/laravel-tackleTackle 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.
SuvenSeo/ai-coding-usage-trackerLocal-first AI coding usage dashboard for Codex, Claude Code, and Cursor — tokens, credits, USD estimates, native GUI, and WakaTime sync.
Doulor/Clawd-CompanionClaude 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。
jianshuo/cchourSee how much time you spend in AI coding tools (Claude Code / Codex) — local HTML report from session logs
cshotwe/oddOutcome-Driven Development for coding agents — declare the outcome, prove it against the real artifact, review the diff like a maintainer.
tashfeenahmed/AgentDomains-skillClaude/agent skill for AgentDNS — free *.makes.fyi subdomains for AI agents
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