kurikomi-labs/komi-learn

README preview

# komi-learn

Continuous memory and self-improvement for coding agents. It learns how you work and recalls it automatically, with no commands. Works with Claude Code and Codex.

[![PyPI](https://img.shields.io/pypi/v/komi-learn)](https://pypi.org/project/komi-learn/)
[![Python](https://img.shields.io/pypi/pyversions/komi-learn)](https://pypi.org/project/komi-learn/)
[![License: MIT](https://img.shields.io/badge/license-MIT-blue)](LICENSE)
[![CI](https://github.com/kurikomi-labs/komi-learn/actions/workflows/ci.yml/badge.svg)](https://github.com/kurikomi-labs/komi-learn/actions/workflows/ci.yml)

It watches a session, distills durable lessons in the background (your style, your stack, fixes that worked), and loads the relevant ones at the start of the next session. No slash commands, nothing to save by hand.

The idea is from [Hermes Agent](https://github.com/nousresearch/hermes-agent); this is my own take, generalized across hosts with an optional shared layer (the community pool, below).

It's early. The core loop is built and CI-tested, but it hasn't been battle-tested across a lot of real sessions yet. Feedback and bug reports are welcome.

## Install

```bash
pip install komi-learn
komi-learn install            # or: komi-learn install --host codex

View full repository on GitHub →