Privacy first toolkit for analyzing your ChatGPT and Claude exports. Model tracking, prompt effectiveness analysis, cost efficiency metrics (POD/DLOD/POE), topic classification, and industry benchmarks. 49 tests. pip installable. Everything runs locally.

• Updated Jun 8, 2026
• Python

Understand how your brand shows up in LLM responses.

• Updated Mar 25, 2026
• TypeScript

Langfuse MCP server with built-in analytics. 34 tools — traces, observations, sessions, scores, prompts, datasets + accuracy metrics, failure detection, token percentiles, cost breakdowns, latency analysis, context breach scanning. Works with Claude Code, Cursor, Codex.

• Updated Apr 21, 2026
• Python

Production-grade Modern Data Stack (MDS) pipeline built with Prefect, dbt, and Postgres. Features least-privilege DB hardening, semantic query caching (ChromaDB + OpenAI) for AI analytics, and complete containerization.

• Updated Jun 1, 2026
• Jupyter Notebook

Self-hosted LLM cost analytics & optimization dashboard. Track OpenAI & Anthropic API spend, tokens, and latency with a 3-line Python SDK. Budgets, forecasting, and savings recommendations.

• Updated May 31, 2026
• Python

Local, single-file HTML dashboard for Claude Code usage and estimated USD cost — token totals across all classes (input/output/cache), per-model spend at list API prices, live current-day data, MCP activity, web research, AI-clustered themes. One uv-runnable Python script.

• Updated May 13, 2026
• Python

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like AI Agent, LLM and tools tracing, debugging multi-agentic system, self-hosted dashboards and advanced analytics with timeline and execution graph view.

• Updated Feb 19, 2025
• Python