AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

ao92265/claude-observatory

Local-first observability + closed-loop self-improvement for Claude Code. HealthDoctor (live hook timeline) + HealthCheck (recommender + A/B + auto-PR).

Python OTHER GitHub ↗ site ↗
★ 0
stars
75
AI relevance
65
solo dev
0
tool sigs

SUMMARY AI summary by gpt-5-mini

Claude Observatory is a local-first toolkit for observability and automated optimization of Claude Code projects. It targets developers and teams embedding Claude Code who need visibility into hook/tool activity and actionable cost/behavior fixes without sending data off-machine. Key features: - HealthDoctor: a drop-in shim that logs every hook, tool call, stdio and timing into a local SQLite store; provides a terminal TUI and a web UI (FastAPI) for live timelines, filtering, and raw JSON inspection. Installable/uninstallable and fail-safe. - HealthCheck: deterministic rules engine that reads JSONL transcripts and emits ranked suggestions (unused tools, opus-costs, low cache-hit, weak CLAUDE.md, high tool concentration), with confidence, projected savings, diffs, A/B test harness, and optional auto-PR creation. - Architecture: robust JSONL parser, WAL-mode SQLite for concurrent access, pure rules; privacy-first (no telemetry).

DETECTED Detected AI stack

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.

🤖 LLM models (1)
Claude
💾 Databases (1)
SQLite
🌐 Web frameworks (1)
FastAPI

Language breakdown (by bytes)

HTML
4.2%
Shell
2.8%
Python
93%

Owner

Account
ao92265
Type
User
Followers
1

Full-Stack Software Engineer · TypeScript · NestJS · React · Prisma · Building secure, multi-tenant SaaS platforms at scale

Dates

Created on GitHub 2026-05-13
Last push 2026-05-13
First seen here 2026-05-13
Last fetched 2026-05-13 16:12

Similar repos (same language)

bgzhang1/sw2api

Reverse proxy for your ai quota from the SW platform.

Python 19 AI 45
dea6cat/2b-agent

This llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus

Python 1 AI 75
Zuboy/Carbon-Cost-Optimizer-Agentic-AI

An AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.

Python 1 AI 75
FuchaZ/lm-studio-vision-bridge

给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务

Python 1 AI 45
Shrutirowlo/AI-Video-Agent

AI-powered video generation agent that automates script analysis, scene planning, and video creation.

Python 1 AI 75
Shivang0/social-vision

Paste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.

Python 1 AI 70
markusbegerow/claude-fuer-oeffentliche-verwaltung

⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.

Python 1 AI 75
knowledgegut/course-distiller

把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF;最後的重組交還人腦。A Claude Code skill by 知識包小腸.

Python 1 AI 45