Show HN: Komi-learn – continuous memory and self-improvement for coding agents

Category: devtools

Tags: coding-agents, memory, self-improvement

Score: 6.5/10 (Innovation: 6, Technical: 7, Documentation: 7, Utility: 6)

Komi-learn is a tool that gives coding agents continuous memory and self-improvement by automatically distilling lessons from user sessions and recalling them in future sessions. It integrates with Claude Code and Codex, featuring an optional community pool for sharing general learnings, making it a novel approach to agent workflow optimization.

Target audience: backend devs

Repository: https://github.com/kurikomi-labs/komi-learn · Python · MIT · 1 stars

View on Hacker News