Skip to content

docs: update tagline + drop emoji #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rainxchzed merged 1 commit into from
May 30, 2026
+3 −5
Merged

docs: update tagline + drop emoji #3

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 3 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,15 @@
# komi-learn

**Your AI agent, minus the amnesia.**
**Continuous memory + self-improvement for AI agents.** Learns how you work, recalls it automatically, no commands. Claude Code & 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)

Today's agents start every session from zero — re-learning your preferences, re-deriving the same workarounds, repeating corrected mistakes. **komi-learn** fixes that: it quietly watches how you work, distills the durable lessons (your style, your stack, techniques that pan out) in the background, and reloads the relevant ones into every new session — **automatically, with no commands to type.**
**komi-learn** quietly watches how you work, distills the durable lessons (your style, your stack, techniques that pan out) in the background, and reloads the relevant ones into every new session — automatically, with no commands to type. One command to set up; then it just runs.

Works with **Claude Code** and **OpenAI Codex**. One command to set up; then it just runs.

> Inspired by [Hermes Agent](https://github.com/nousresearch/hermes-agent)'s self-improvement loop — rebuilt to be model-agnostic, universal, and *shareable* (see the community pool below). Early days — feedback very welcome. 🙏
> Inspired by [Hermes Agent](https://github.com/nousresearch/hermes-agent)'s self-improvement loop — rebuilt to be model-agnostic, universal, and *shareable* (see the community pool below). Early days — feedback very welcome.

---

Expand Down
Loading