by kurikomi-labs · Codex Skill · ★ 60
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. 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; this is my own take, generalized across hosts with an optional shared layer (the community pool, below). It's early.
| Stars | 60 |
| Forks | 0 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 72.2023446665854/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-09 |
| Created | 2026-05-29 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~36k |
These tools work well together with komi-learn for enhanced workflows:
Explore other popular codex skill tools:
komi-learn is Continuous memory + self-improvement for AI agents. Learns how you work, recalls it automatically, no commands. Claude Code & Codex.. It is categorized as a Codex Skill with 60 GitHub stars.
komi-learn is primarily written in Python. It covers topics such as ai, ai-agents, ai-tools.
You can find installation instructions and usage details in the komi-learn GitHub repository at github.com/kurikomi-labs/komi-learn. The project has 60 stars and 0 forks, indicating an active community.
komi-learn is released under the MIT license, making it free to use and modify according to the license terms.