7df-lab/devo

A self-improving agent. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills.

Latest release v0.2.16 · 20 Oct 2026

1 file for Codex and OpenCode: devo AGENTS.md — 1,652 tokens loaded in every session.

Open on GitHub devo.7df.ai

345Stars on the repository

1Files it configures its agents with

1,652Tokens loaded in every session

2Agents configured

Instructions

devo AGENTS.md AGENTS.md A 1,652 tok

These files are 7df-lab/devo'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.