Agent-driven development with a learning loop. Few opinionated agents + thin skills + confidence-decaying learnings. Pure markdown, zero dependencies.
-
Updated
Apr 11, 2026 - Shell
Agent-driven development with a learning loop. Few opinionated agents + thin skills + confidence-decaying learnings. Pure markdown, zero dependencies.
completion-learn: post-task learning loop for finished work, ordered as self → collaboration → tool.
Qomni Engine v8: Adaptive Cognitive OS — Crystal Distillation + CRYS-L v2 (open) + Learning Loop Planner · Percy Rojas Masgo, Qomni AI Lab
A cognitive layer for Claude Code — inspired by how brains actually work
Qomni Planner v0.59: Adaptive Cognitive Routing with Online Learning Loops for Edge AI Inference — Percy Rojas Masgo, CEO Condesi Perú · Qomni AI Lab
Lightweight multi-agent development workflow plugin for Claude Code
Multi-agent coding OS — BMad pipelines, Karpathy wiki, closed learning loops, dual-runtime coordination (Claude + Codex)
Add a description, image, and links to the learning-loop topic page so that developers can more easily learn about it.
To associate your repository with the learning-loop topic, visit your repo's landing page and select "manage topics."