Enterprise DNA
M MCP Servers Developer low

LWTlong/ai-dev-analytics

by Various

An open-source AI coding observability layer. Silently tracks vibe coding sessions via MCP and codifies AI deviations into project rules. 100% local.

L

MCP

LWTlong/ai-dev-analytics

Added 1 June 2026

Overview

An open-source TypeScript tool that silently tracks AI coding sessions via the Model Context Protocol. It logs deviations from project rules during vibe coding and codifies those deviations into updated rules, all running 100% locally.

Best for

Best for
Developers using AI coding assistants who want to enforce and evolve project rules locally

Use cases

  • Monitor how AI assistants deviate from established project conventions
  • Automatically update project rules based on observed AI behavior
  • Audit local AI coding sessions without sending data to external servers

Notes

An open-source TypeScript tool that silently tracks AI coding sessions via the Model Context Protocol. It logs deviations from project rules during vibe coding and codifies those deviations into updated rules, all running 100% locally.

7 stars on GitHub. Last updated 2026-05-25. Licensed MIT.

Use cases

  • Monitor how AI assistants deviate from established project conventions
  • Automatically update project rules based on observed AI behavior
  • Audit local AI coding sessions without sending data to external servers

Pros

  • Fully local operation ensures data privacy
  • Automates rule maintenance from real AI usage patterns
  • Lightweight observability layer for AI-assisted development

Cons

  • Very early stage with only 7 GitHub stars and limited community
  • Requires MCP integration which may not work with all AI tools
  • No documented support for non-TypeScript projects or complex rule formats

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Fully local operation ensures data privacy
  • Automates rule maintenance from real AI usage patterns
  • Lightweight observability layer for AI-assisted development

Cons

  • Very early stage with only 7 GitHub stars and limited community
  • Requires MCP integration which may not work with all AI tools
  • No documented support for non-TypeScript projects or complex rule formats