GPUs for Your Agent

givemeanode Skip to contentGive your agent GPUs. Givemeanode is a slurm-like GPU orchestrator built for AI agents like claude, codex, or opencode. It’s everything you need for autoresearch. Queue up thousands of jobs on large scale GPU clusters, get billed by the minute. Read the docs. claudecodexcursoropencodemcpmoredevincapyampoh my pizedclaude mcp add --transport http givemeanode https://mcp.givemeanode.comcopy Using Claude in the browser? Go to Settings, Connectors, Add custom connector and enter the remote MCP server URL https://mcp.givemeanode.com.

codex mcp add givemeanode --url https://mcp.givemeanode.comcopy

In ~/.cursor/mcp.json: "mcpServers": { "givemeanode": { "url": "https://mcp.givemeanode.com" } }copy

In opencode.json (project or global): "mcp": { "givemeanode": { "type": "remote", "url": "https://mcp.givemeanode.com", "enabled": true }copy

https://mcp.givemeanode.comcopy

devin mcp add givemeanode https://mcp.givemeanode.comcopy Or in ~/.config/devin/config.json: "mcpServers": { "givemeanode": { "url": "https://mcp.givemeanode.com", "transport": "http" } }copy

In Capy, go to Settings, MCP servers, New MCP server, pick the HTTP transport, and enter the server URL: https://mcp.givemeanode.comcopy Then open the saved server and click Connect to finish the OAuth sign-in.

In ~/.config/amp/settings.json (or the Amp extension settings in VS Code): "amp.mcpServers": { "givemeanode": { "url": "https://mcp.givemeanode.com" } }copy

In ~/.omp/agent/mcp.json (or a project's .omp/mcp.json). /mcp add in a session does this for you: "mcpServers": { "givemeanode": { "type": "http", "url": "https://mcp.givemeanode.com" } }copy

In Zed's settings.json (zed: open settings from the command palette): "context_servers": { "givemeanode": { "url": "https://mcp.givemeanode.com" } }copy Zed prompts for the OAuth sign-in on first use.

“I LOVE givemeanode. I’ve been running astrophysics jobs on it. The agent-first design is amazing and the ticket experience has been remarkable.” — Zack, UC Berkeley / LBNL ❀ ❀ ❀ Make anyone a machine learning researcher Each of these is one sentence to your agent. The docs show every example as English, CLI, and the MCP calls underneath. Run anything on an H100 in one sentence You say to your agent“Get me a GPU node, clone github.com/you/yourrepo on it, and run the benchmark.” A container on an H100 with a persistent disk, billed by the minute. See nodes.

Fine-tune a model overnight You say to your agent“Start the fine-tune on the node in the background, check the loss every hour, and stop the node when it converges.” Training runs detached and outlives the conversation. Stopping the node stops the bill with the files intact, like tmux on a machine you can power off. See long-running commands.

Sweep and evaluate as batch jobs You say to your agent“Sweep learning rates 1e-4, 3e-4, and 1e-3 over the training job as a batch, and show me a results table when they finish.” Up to 256 variants in one call, billed only while running, with queued time free. Jobs can checkpoint, so a preempted run resumes where it left off and you pay only for progress that survives. Each job declares its result as JSON, so a finished sweep reads as a table. See batch jobs.

❀ ❀ ❀ Vastly more efficient ML development The usual setup is a dev box rented around the clock, with the agent running inside it over ssh. Most of what an agent does is thinking: reading code, planning, editing. While it thinks, the GPU sits idle, and the meter keeps running. Using a dev box ~$2,900 / month

The agent lives inside the box, so the GPU is reserved for every minute of thinking, and one box means one experiment at a time. DEV BOXRENTED 24/7AGENTGPUBILLED: ALWAYSIDLE: FREQUENTLYUsing GMAN ~$240 / month

The agent runs on your laptop or in the cloud and takes a node for each burst of real GPU work. When it is time to scale, it fans out across many nodes at once. YOUR AGENTGPU NODES, BY THE MINUTEBILLED: BURSTS ONLYIDLE: $0

❀ ❀ ❀ Pricing ItemRateMinimum / free tierDiscount1×H100 node$0.0666/min ($3.996/hr)--8×H100 node$0.5328/min ($31.968/hr)--Batch jobs (H100)$0.04995/min per GPU-25% below interactiveJob builds$0.01/min300 min/month free-Logs$0.50/GB ingested5 GB/month free-Metrics$8 per 1,000 active series/monthfirst 10,000 series free-Traces$0.50/GB ingested5 GB/month free-Snapshot storage$0.10/GiB-month250 GiB free-Object storage$0.10/GB-month100 GB free-

GPUs for Your Agent

Related Articles

(no title)

Scientists reverse brain aging, with a nasal spray

NHS apologises and admits Palantir have access to identifiable patient data

AI has torched the market for junior programmers

Al Vigier: Canada's AI strategy shouldn't include secret Palantir bills