shuxuecode/claude-watch
Stream Claude Code's hidden output (thinking, tool calls, subagents) to a web browser in real-time.
SUMMARY AI要約 by gpt-5-mini
claude-watch is a small tool that tails Claude Code’s JSONL session logs (~/.claude/projects/) and streams the internal activity (thinking blocks, tool calls/results, subagents, tokens) to a local web dashboard in real time. It’s aimed at developers and operators who need visibility into what Claude Code agents are doing for debugging, auditing, or observability. Key features: - Real-time streaming of thinking, tool input/output, hook output, and text - Multi-session tree view with auto-discovery of new sessions - Nested subagent tracking and agent-level active indicators - Color-coded session tags, session hiding (24h), auto-collapse - Token/cost visibility and context-window utilization - Independent filters for event types, code-block copy, configurable polling/ports - CLI launcher (npm install -g claude-code-watch), host/port and session options, env var CLAUDE_HOME to override path.
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。
使用言語(バイト数比)
オーナー情報
Learning Learning Learning
日付
| GitHub作成日 | 2026-05-10 |
| 最終Push | 2026-05-10 |
| 当サイト初検出 | 2026-05-10 |
| 最終取得 | 2026-05-10 16:11 |
類似Repo (同じ言語のAI関連Repo)
Box — self-hosted Claude Code in your pocket. Run real Claude Code & Codex sessions on your own server, driven from your phone (native chat UI, voice, files, skills, always-on).
mohamedzhioua/proofguardKill-tested guard skills for AI coding agents , self-invoking quality gates that catch AI failure modes in security, tests, docs, dependencies, and diffs before the agent says "done." Works with Claude Code, Codex, and Cursor.
IFTC-XLKJ/aiproxy renezander030/blender-cliDrive Blender headless from your AI agent: scaffold, build, animate from natural language. JSON in, JSON out.
muhammad1-wq/mechapulseAI ROBOTICS COMPANY
aditya89bh/ai-guardrails-explanations-design-systemA documentation-first design system for enterprise AI teams building trust and safety into AI products — patterns for warnings, explanations, permissions, uncertainty, refusal, escalation, and recovery.
the-snowmen/fresh-eyesA cast of fictional external users who review your running app in a real browser — isolated from your code, so the feedback stays honest. A Claude Code plugin.
pratik-chiwande/E-commerceI made Ecommerce site using tailwind-css ,React, also used Claude and Chatgpt