Elyan Compute logo

Elyan Compute

Community
Scottcjn
elyan-compute

Submit inference, vision, text-to-speech, and video generation jobs to Elyan Labs GPU compute endpoints (V100, RTX 5070, POWER8) via x402 USDC micropayments on Base chain. Use when the user wants to run remote inference, rent cloud GPU compute, generate images or video, convert text to speech, or access pay-per-request GPU endpoints.

Overview

PublisherScottcjn
Repositoryelyan-compute-skill
Skill nameelyan-compute
Stars
71
Forks
5
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Scottcjn on GitHub. Read the source before you install it.

Installation

Install the Elyan Compute AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Scottcjn/elyan-compute-skill/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Scottcjn/elyan-compute-skill.git \
  .claude/skills/elyan-compute
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Elyan Compute in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Elyan Compute on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Elyan Compute is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Elyan Labs Compute Marketplace

Submit compute jobs to Elyan Labs' GPU infrastructure in Baton Rouge, LA. All endpoints use x402 USDC micropayments on Base (chain 8453).

Request Lifecycle

  1. Send a POST request to the endpoint with the required JSON body.
  2. If no payment is attached, the endpoint returns HTTP 402 with x402 payment requirements.
  3. The x402_fetch tool handles USDC payment automatically on Base chain.
  4. On success, the endpoint returns HTTP 200 with the result (JSON for inference/vision, WAV audio for TTS, video URL for video).
  5. On failure, expect HTTP 400 (malformed request), HTTP 402 (payment failed or insufficient), or HTTP 503 (GPU unavailable). Retry 503 after a brief delay.

Available Endpoints

LLM Inference — $0.01/request

POST http://50.28.86.131:8070/beacon/api/compute/inference
Content-Type: application/json

{"model": "llama3.2:3b", "prompt": "Your prompt here", "system": "optional system prompt"}

Hardware: IBM POWER8 S824, 512GB RAM, 128 threads. Models: llama3.2:3b, llama3.1:8b, qwen2.5:14b, deepseek-r1:32b.

Vision Understanding — $0.05/request

POST http://50.28.86.131:8070/beacon/api/compute/vision
Content-Type: application/json

{"image_url": "https://example.com/photo.jpg", "prompt": "Describe this image"}

Hardware: BAGEL-7B-MoT on V100 16GB (NF4 quantized).

Text-to-Speech — $0.02/request

POST http://50.28.86.131:8070/beacon/api/compute/tts
Content-Type: application/json

{"text": "Hello world", "language": "en"}

Hardware: XTTS on RTX 4070 8GB. Returns WAV audio.

Video Generation — $0.50/request

POST http://50.28.86.131:8070/beacon/api/compute/video
Content-Type: application/json

{"prompt": "A robot walking through a swamp at sunset", "width": 720, "height": 720}

Hardware: LTX-2 / ComfyUI on V100 32GB.

Response Validation

  • Inference/Vision: Verify the JSON response contains a non-empty response or result field before presenting to the user.
  • TTS: Confirm the returned WAV data is non-empty (Content-Length > 0) before saving or playing audio.
  • Video: Check that the response includes a valid URL and that the video file is accessible before sharing with the user.

Alternative Payment

Also accepts RustChain RTC via X-RTC-Payment header (1 RTC = $0.10 USD).

Discovery

  • Agent Card: http://50.28.86.131:8070/beacon/.well-known/agent-card.json
  • Compute Catalog: http://50.28.86.131:8070/beacon/api/compute/catalog
  • x402 Pricing: http://50.28.86.131:8070/beacon/api/x402/pricing

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Elyan Compute AI skill do?

Submit inference, vision, text-to-speech, and video generation jobs to Elyan Labs GPU compute endpoints (V100, RTX 5070, POWER8) via x402 USDC micropayments on Base chain. Use when the user wants to run remote inference, rent cloud GPU compute, generate images or video, convert text to speech, or access pay-per-request GPU endpoints.

Why use Elyan Compute on TypingMind?

Because you install it once and use it with any model. Elyan Compute is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Elyan Compute in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Scottcjn/elyan-compute-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Elyan Compute?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Elyan Compute?

As many as you like. As long as a model supports skills, you can use Elyan Compute with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Elyan Compute AI skill free?

Yes. It is published on GitHub by Scottcjn under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇