← ランキング · AI関連リポジトリ

skatrych/offline-claude

Start Claude Code in a 100% Privacy Mode, in a completely network-wise isolated environment that prevents any call-back-home (telemetry or logging) which may exist for whatever purpose. Offline-claude has access only to a Local AI server (e.g. ollama).

Shell GitHub ↗

★ 0

stars

AI関連スコア

個人開発度

AIツール痕跡

SUMMARY AI要約 by gpt-5-mini

offline-claude packages Claude Code into a Docker compose setup that is network-isolated so the container can only reach a local Ollama instance (127.0.0.1:11434 or a LAN host). It’s aimed at developers who need to run Claude Code fully offline/air‑gapped on macOS (OrbStack or Docker Desktop). Key features: - Internal-only Docker network with an nginx ollama-proxy bridging container→host - Per-project workspace mounted into the container and per-project state at ~/.offline-claude/projects/<project-id>/.claude - CLI wrapper (~/bin/offline-claude) with model selection and OLLAMA_HOST support - Read-only shared mounts configurable in docker/compose.yaml - Build/update scripts, telemetry/feedback disabled, and Docker-enforced isolation (no access to cloud creds or user secret dirs)

DETECTED 検出されたAIスタック

このRepoのdescription / GitHub topics / READMEのAI要約に出現したAI関連キーワードをカテゴリ別に表示。各バッジは該当カテゴリの詳細ランキングへリンクします。

🧠 LLMプロバイダー (1)

Ollama

🤖 LLMモデル (2)

Claude Llama

使用言語(バイト数比)

Shell

88%

Dockerfile

12%

AI関連と判定した根拠

AI関連スコアは4つの箇所それぞれにAI関連キーワードが現れるかを判定し、該当した配点を合計したものです。算出方法の詳細

リポジトリ名該当なし

説明文 +25 一致: ai

GitHub Topics 該当なし

README冒頭 +20 (スコアから逆算 — README本文は保存していません)

合計 AI関連スコア: 75 / 100

同じ言語のAI関連Repoの中での位置

当サイトが追跡している Shell 製Repoは 962件 (うちAI関連スコア40以上は 847件)。このRepoより スター数が多いのは 243件 (上位 25.4%)、 AI関連スコアが高いのは 85件 (上位 8.9%) です。

オーナー情報

アカウント

skatrych

タイプ

User

フォロワー

Senior Software Architect, Blockchain Engineer, DevSecOps fan, Agentic AI enthusiast.

日付

GitHub作成日	2026-05-14
最終Push	2026-05-14
当サイト初検出	2026-05-14
最終取得	2026-08-18 16:22

類似Repo (同じ言語のAI関連Repo)

JamesShi96/project-butler

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

Shell ★ 372 AI 70

99xAgency/GodModeSkill

Multi-LLM cross-review workflow for Claude Code. /work orchestrates plan/implement/bug-fix with 3 different model families voting on every gate.

Shell ★ 239 AI 45

Heoooooon/lazy-starter-kit

A signed GUI and one safe command to turn macOS, Linux, or Windows into a complete AI development environment — dry-run first, repeatable, and tested.

Shell ★ 79 AI 70

Avanderheyde/levelsio-vps-setup-skill

A Claude Code skill to deploy and operate a web app on a single cheap, hardened VPS the levels.io way — Hetzner/DigitalOcean + Next.js + SQLite + Caddy + systemd.

Shell ★ 42 AI 70

MeherBhaskar/agent-rigor

Skill repository to enforce Engineering disclipline in coding assistants

Shell ★ 41 AI 75

alicicek/tale-mode

A discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes. Built by Fable to make any Claude work like a careful senior engineer.

Shell ★ 36 AI 60

anzy-renlab-ai/pronounce

🔊 Pronounce developer jargon out loud. 1,650+ entries (kubectl, GIF, JSON, JWT, …), sourced with confidence levels. Bash CLI + VS Code extension + interactive quiz + voice search + MCP server + Claude Code skill.

Shell ★ 33 AI 70

AbuZar-Ansarii/All-Agents

Install and run every AI agent on your phone locally

Shell ★ 32 AI 45