All activity
AI coding agents can't feel when they're stuck.
They'll retry the same broken fix five times because they can see each error but not the pattern. Metacog is a Claude Code hook that watches for these loops, and six other failure modes, silently.
When things go wrong, it nudges the agent to reflect. When problems resolve, it learns what fixed them. Most memory systems prune rules that stop firing. Metacog treats that silence as proof the rule worked.
Zero dependencies. One-command install.
MetacogStops your agents repeating the same mistakes.
Richard Baxterleft a comment
Thanks for checking this out. I've been watching it watch my Claude Code sessions and actively iterating on what it does. It started as six senses detecting failure patterns, and it's already grown to seven (scope drift detection), plus session retrospectives and user interaction tracking to give feedback to the user at session end, all from observing where it helped and where it fired false...
MetacogStops your agents repeating the same mistakes.
Houtini is the local sidekick for your AI. It offloads heavy tasks from models like Claude to your local machine via LM Studio. Stop worrying about API bills and context limits. Keep your workflow fast, private, and powerful.
Houtini.aiHoutini: Your AI's Local Superpower
Richard Baxterleft a comment
Hey Product Hunt! 👋 I'm Richard, the maker of Houtini. I'm so excited to share this project with you all today. The Problem: Like many developers, I've integrated AI deep into my workflow. I primarily use models like Claude, and while they're fantastic, I constantly ran into two major frustrations: Thread Limits: Trying to analyze or refactor large codebases would often hit context window...
Houtini.aiHoutini: Your AI's Local Superpower