ashlraiashlrai/ashlr-md/landing/llms.txt

ashlr-md / landing

llms.txt4 starsChanged 5 months agoMITView on GitHub

Open-source Markdown app for macOS, Windows, and Linux. Agents install one command, call a CLI that prints JSON, and drive the live document over MCP. Ashlr MD is a desktop app plus mdopen and the mdopener-mcp server. People read and edit .md files. Agents open, edit, export, and request a human review. The install command, from a checkout on macOS or Linux:

In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- landing/llms-full.txtllms.txt
- llms-full.txtllms.txt
- llms.txtllms.txt

The file

Create a free account to mount

Files

llms.txt

# Ashlr MD

> Open-source Markdown app for macOS, Windows, and Linux. Agents install one command, call a CLI that prints JSON, and drive the live document over MCP.

Ashlr MD is a desktop app plus `mdopen` and the `mdopener-mcp` server. People read and edit `.md` files. Agents open, edit, export, and request a human review.

The install command, from a checkout on macOS or Linux:

```bash
SKIP_APP_BUILD=1 bash scripts/install.sh
```

Then:

```bash
mdopener-mcp doctor --json
mdopener-mcp setup --local --json
mdopener-mcp --ashlr-handshake --json
claude mcp add --scope user ashlr-md "$(command -v mdopener-mcp)"
codex mcp add ashlr-md -- "$(command -v mdopener-mcp)"
python3 scripts/connect-cursor.py
```

## Start

- [README](https://github.com/ashlrai/ashlr-md/blob/main/README.md): what it is, the install command, the JSON commands, and the MCP snippets
- [Copy-paste examples](https://github.com/ashlrai/ashlr-md/blob/main/docs/EXAMPLES.md): every command, including Windows
- [Full agent guide](https://github.com/ashlrai/ashlr-md/blob/main/llms-full.txt): the same material in one file
- [MCP tool contract](https://github.com/ashlrai/ashlr-md/blob/main/docs/AGENTS.md): every tool, in server order
- [Install a release](https://github.com/ashlrai/ashlr-md/blob/main/docs/INSTALL.md): macOS, Windows, and Linux downloads

## CLI

- [doctor --fix](https://github.com/ashlrai/ashlr-md/blob/main/docs/doctor-fix.md): `mdopener-mcp doctor --fix --json` previews repairs and writes nothing
- [Handshake](https://github.com/ashlrai/ashlr-md/blob/main/docs/ashlr-handshake.md): `mdopener-mcp --ashlr-handshake --json`
- [Local AI](https://github.com/ashlrai/ashlr-md/blob/main/docs/local-ai.md): `localInference`, offline mode, and base URL rules
- [Phantom](https://github.com/ashlrai/ashlr-md/blob/main/docs/PHANTOM.md): how Phantom calls `mdopen`

## Optional

- [Docs index](https://github.com/ashlrai/ashlr-md/blob/main/docs/README.md): the rest of the guides
- [Vision](https://github.com/ashlrai/ashlr-md/blob/main/docs/VISION.md): the product goal
- [Security](https://github.com/ashlrai/ashlr-md/blob/main/SECURITY.md): threat model
- [Obsidian](https://github.com/ashlrai/ashlr-md/blob/main/docs/OBSIDIAN.md): vault notes, wikilinks, and the Open in Ashlr MD plugin
- [Contributing](https://github.com/ashlrai/ashlr-md/blob/main/CONTRIBUTING.md): how to send a change

## Product and plans

- [README](README.md): project overview and agent setup.
- [Vision](docs/VISION.md): the product goal.
- [Roadmap](ROADMAP.md): planned work and the build loop.
- [Changelog](CHANGELOG.md): user-visible changes.
- [Install guide](docs/INSTALL.md): installation and command-line setup.

## Agent integration

- [Agent guide](docs/AGENTS.md): the MCP tool contract and CLI.
- [Phantom integration](docs/PHANTOM.md): how Phantom opens Markdown.
- [MCP discovery metadata](docs/mcp-registry.md): server registry metadata.
- [Agent contribution rules](AGENTS.md): repository instructions for agents.

## Editor and app integrations

- [Obsidian compatibility](docs/OBSIDIAN.md): supported vault features.
- [VS Code extension](integrations/vscode/README.md): open Markdown from VS Code.
- [Obsidian plugin](integrations/obsidian/README.md): open notes from Obsidian.
- [Raycast extension](integrations/raycast/README.md): open recent Markdown files.

## Contributing and security

- [Contributing](CONTRIBUTING.md): development and checks.
- [Security policy](SECURITY.md): vulnerability reporting and threat model.
- [Release process](docs/RELEASING.md): release runbook.
- [Post-quantum readiness](docs/PQ-READINESS.md): cryptography inventory and migration considerations.

## Samples

- [Showcase](samples/showcase.md): supported Markdown features.
- [Agent plan sample](samples/agent-plan.md): an example agent plan.

## More resources

- [Landing page readme](landing/README.md): landing page development.
- [Historical Linux probe](docs/NATIVE-QA-PROPOSAL.md): a bounded historical qualification proposal.
- [Historical Windows qualification](docs/WINDOWS-NATIVE-QA.md): a bounded historical qualification proposal.

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.

Check your setup, free