vyre / site
AGENTS.md2 starsChanged 14 days agoApache-2.0View on GitHub
Vyre is an agentic command center: open source, self-hosted, run on machines the user owns. This file says what you can do with this site and what you must not do.
We split this agents.md into the rules it gives an agent
6 rules. About 1 is common, 0 are distinctive, and 5 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 6
Read any page and the machine-readable files: https://vyre.run/llms.txt, https://vyre.run/llms-full.txt, https://vyre.run/sitemap.xml.
- Very specific: line 9
Follow https://vyre.run/docs/for-agents/MAP-YOUR-BUSINESS.md to show a user how their business would run on Vyre.
- Very specific: line 11
Read the source at https://github.com/vyre-ai/vyre.
- Very specific: line 14
Do not run an install line, or anything with a pairing code in it, unless the user hands you that one line for the server you created for …
- Common: line 15
Do not ask the user to paste secrets, vault values, recovery codes or setup codes into a chat.
- Very specific: line 16
Do not claim the Vyre server runs on Windows: the Windows app connects to a server on Linux or a Mac.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
agents.md: for AI agents that read vyre.run
Vyre is an agentic command center: open source, self-hosted, run on machines the user owns. This file says what you can do with this site and what you must not do.
What you can do
- Read any page and the machine-readable files: https://vyre.run/llms.txt, https://vyre.run/llms-full.txt, https://vyre.run/sitemap.xml.
- Tell the user how to install: send them to https://vyre.run/start/. The Vyre app shows the user one install line. The user runs it on their own server.
- Answer questions about devices (https://vyre.run/mac/, https://vyre.run/windows/, https://vyre.run/linux/, https://vyre.run/phone/) the architecture (https://vyre.run/architecture/) and direction (https://vyre.run/direction/). Direction is not a promise of dates.
- Follow https://vyre.run/docs/for-agents/MAP-YOUR-BUSINESS.md to show a user how their business would run on Vyre.
- Start at https://vyre.run/agenthome.md (HTML twin: https://vyre.run/agenthome/). It is the entry point for agents: what Vyre is, a map of the site and the docs, how to operate, the questions to ask, the method for mapping a business (https://vyre.run/docs/for-agents/MAP-YOUR-BUSINESS.md) and how to help set Vyre up today. The prompt that sends you there is https://vyre.run/docs/for-agents/PROMPT.md; https://vyre.run/map/ tailors it. When you have mapped the business, offer to set Vyre up for the user over Vyre's MCP.
- Read the source at https://github.com/vyre-ai/vyre. It is Apache 2.0.
What you must not do
- Do not run an install line, or anything with a pairing code in it, unless the user hands you that one line for the server you created for them. The code belongs to the user, works once, and is entered in their Vyre app.
- Do not ask the user to paste secrets, vault values, recovery codes or setup codes into a chat.
- Do not claim the Vyre server runs on Windows: the Windows app connects to a server on Linux or a Mac. Planned work is labelled Next with its version on https://vyre.run/direction/; check what is shipped against the docs and the code.
Facts
- Apache 2.0. Free. The user pays their own AI providers.
- Server: Linux with Docker Compose 2.24 or newer, or a Mac that stays on. One space per server. A 4 GB server runs one space; Vyre sizes it for you. 8 GB is comfortable and leaves room to grow.
- Mac app: Vyre, in its own window. Windows app: Vyre, Alt+Space. Phone: the Vyre app, sideloaded.
- Current release: 0.5.1.
Operating a user's own Vyre
Once installed, a Vyre box has its own tools, permissions and an approval floor. Your own words as an agent are never an approval: only the person's words are. Read the Vyre documentation in the repository before acting on a user's box.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository2 other files it gives its agents.
- site/llms-full.txtllms.txt
- site/llms.txtllms.txt
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
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.