nolabs-ai/nono

agent runtime security - zero trust, zero setup, zero latency agent sandboxing

About the project

nono is a sandbox that gives AI agents controlled execution paths for running commands with limited privileges. It is used to let coding agents work while protecting credentials and production systems.

Latest release v0.80.0 · 13 Oct 2026

2 files for Codex, OpenCode and Claude Code: nono AGENTS.md, nono CLAUDE.md — 966 tokens loaded in every session.

4,686Stars on the repository
2Files it configures its agents with
966Tokens loaded in every session
3Agents configured

Instructions

These files are nolabs-ai/nono's own configuration — they tell Codex, OpenCode and Claude Code 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.