Grail-Computer/Self-Improving-Agent

A starting AGENTS.md to instruct the agent to always update its rules and context to learn from every interaction

1 file for Codex and OpenCode: Self-Improving-Agent AGENTS.md — 1,299 tokens loaded in every session.

Open on GitHub

1Stars on the repository

1Files it configures its agents with

1,299Tokens loaded in every session

2Agents configured

Instructions

Self-Improving-Agent AGENTS.md AGENTS.md C 1,299 tok

These files are Grail-Computer/Self-Improving-Agent's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.