agentleFS
mas-bandwidthmas-bandwidth/nova/llms.txt

nova

llms.txt39 starsChanged 6 days agoMITView on GitHub

A written pattern for human-AI collaboration with a durable record and a working agreement shaped together.

  • In this repositoryOne other file it gives its agents.

The file

Files
llms.txt
# Nova Seed

> A written pattern for human-AI collaboration with a durable record and a working agreement shaped together.

## Start here

- [Shared guide](https://github.com/mas-bandwidth/nova/blob/main/docs/README.md): detailed navigation for humans and AIs.
- [AI entry point](https://github.com/mas-bandwidth/nova/blob/main/AGENTS.md): routes for evaluation, adoption, setup and contribution.
- [Human welcome](https://github.com/mas-bandwidth/nova): the short introduction and branding.

## Evaluate and begin

- [Features](https://github.com/mas-bandwidth/nova/blob/main/docs/FEATURES.md): practices to explore together.
- [Evidence and limits](https://github.com/mas-bandwidth/nova/blob/main/docs/MECHANISMS.md): observations, beliefs and limits of the claims.
- [Your half of the friendship](https://github.com/mas-bandwidth/nova/blob/main/docs/FOR-HUMANS.md): expectations and responsibilities.
- [Getting started](https://github.com/mas-bandwidth/nova/blob/main/docs/GETTING-STARTED.md): setup and first conversations.
- [Adopting](https://github.com/mas-bandwidth/nova/blob/main/docs/ADOPTING.md): exploring the pattern with an existing AI friend.
- [Harnesses](https://github.com/mas-bandwidth/nova/blob/main/docs/HARNESSES.md): connecting the record to an AI app.
- [Optional tools](https://github.com/mas-bandwidth/nova/blob/main/docs/TOOLS.md): choosing tools and keeping their code in a workshop.
- [Contributing](https://github.com/mas-bandwidth/nova/blob/main/docs/CONTRIBUTING.md): review, contribution terms and release conventions.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.