# COMPUTE.md

> A skill that makes AI agents careful compute buyers: size a model or job before renting anything, get prices from your own providers, launch only inside limits you set, and tear everything down. Version 1.0. MIT.

The skill works offline in any agent. Set your own limits (budget, approval threshold, hourly cap, hard stop, spot policy, model-call budget, providers, regions) and they're written into the file. An optional read-only API and MCP server add sizing estimates and accelerator specs. compute.md lists no prices, and never books, bills or holds credentials.

Use at your own risk. compute.md is provided as is, without warranty. Information here may be inaccurate, incomplete or not current, and is not verified; sizing figures are estimates. Not financial, legal or procurement advice. Confirm everything with your providers before you rent or buy.

## Skill

- [COMPUTE.md](https://compute.md/compute.md): load into your agent's instructions or save as ~/.claude/skills/compute/SKILL.md (sha256 69cf14cd32e9ad3e2694e6b514fa3f8c7ad4f974f152f38177c8bda91d9370b8)
- [COMPUTE.md with your limits](https://compute.md/compute.md?budget_usd=50&approval_usd=10&max_hourly_usd=25&stop_hours=4&spot=checkpointed): every lever is a number or a fixed choice

## API (no key, read-only, CORS open)

- [Fit](https://compute.md/api/v1/fit?model=Qwen/Qwen3.6-27B&context=32768&concurrency=8): memory, the GPUs that fit and estimated speed for serving or fine-tuning any Hugging Face model
- [GPU specs](https://compute.md/api/v1/gpus): memory, bandwidth and throughput from vendor datasheets
- [Models](https://compute.md/api/v1/models): quick-pick model specs; ?id=org/name for any Hugging Face repo
- [API index](https://compute.md/api/v1) and [OpenAPI](https://compute.md/openapi.json)

## MCP

- https://compute.md/mcp: Streamable HTTP, stateless, no auth. Tools: fit_model, gpu_specs, model_spec. Prompt: compute, with optional limit arguments.

## Terms

- [Terms of use and disclaimer](https://compute.md/terms)

## Optional

- [Full text](https://compute.md/llms-full.txt): the skill plus the API reference
- [Manifest](https://compute.md/.well-known/compute.json)