AGENTS.md@desktop agentsB
AGENTS.md@desktop is agent-read markdown (agents) from ginlix-ai/langalpha.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# langalpha desktop Electron shell around the hosted web app. It is a **remote-URL wrapper**: the package contains Electron, `src/`, two local pages and an entry URL, and nothing else. No web bundle ships with it, so a web deploy never needs a desktop release. The two local pages are the ones that have to work when the network does not: the OSS server picker and the outage screen. > Single source of truth for AI coding agents in `desktop/`. Edit here. ## Why Electron, not Tauri Both were built and measured. On macOS the performance is comparable, so speed is not what decided it: what is left is a straight trade of package size and idle memory, where Tauri wins outright, against engine control and shell cost, where Electron does. **Engine control is worth more here than it would be in a bundled app.** This wrapper carries no web bundle, so under Tauri the rendering engine becomes whatever the user's OS ships. WebView2 on Windows is Chromium and fine; macOS pins to that machine's WKWebView and Linux to WebKitGTK, for a payload that deploys weekly and cannot be version-matched to any of them. Electron puts one Chromium inside the package and moves …
Read the whole file at its exact version.
How to install
mdr add ginlix-ai/langalpha/desktop/AGENTS.md@git:20260904.3e9f6b7mdr add ginlix-ai/langalpha/desktop/AGENTS.md@sha256:34433e6b98af8672Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_x7h7nnpxhwaw5y57)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260904.3e9f6b7 latest | 2026-09-04 | 3e9f6b7 | 28,650 B | B | view · diff |
| git:20260903.340ea62 | 2026-09-03 | 340ea62 | 27,836 B | B | view · diff |
| git:20260903.86b7663 | 2026-09-03 | 86b7663 | 27,275 B | B | view · diff |
| git:20260827.1d26e4e | 2026-08-27 | 1d26e4e | 24,145 B | B | view · diff |
| git:20260820.c190623 | 2026-08-20 | c190623 | 22,865 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:8000)
- pass: Size between 200 bytes and 200 KB (28650 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No script tag
Source
ginlix-ai/langalpha · 1,774 stars · license Apache-2.0 · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_x7h7nnpxhwaw5y57 GET https://markdownregistry.com/api/v1/resolve?ref=ginlix-ai/langalpha/desktop/AGENTS.md GET https://markdownregistry.com/api/v1/blob/34433e6b98af86723d283de3b2247468b355b084f09af25e1ed1f9a9f0c773b8
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from ginlix-ai/langalpha
Every file in ginlix-ai/langalpha