The platform for autoresearch
Give your LLM a supercomputer. Get thousands of GPUs on the only PaaS designed for agent-driven machine learning.
$ claude mcp add --transport http givemeanode https://mcp.givemeanode.comUsing 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.comIn ~/.cursor/mcp.json:
{
"mcpServers": {
"givemeanode": { "url": "https://mcp.givemeanode.com" }
}
}In opencode.json (project or global):
{
"mcp": {
"givemeanode": {
"type": "remote",
"url": "https://mcp.givemeanode.com",
"enabled": true
}
}
}https://mcp.givemeanode.com$ devin mcp add givemeanode https://mcp.givemeanode.comOr in ~/.config/devin/config.json:
{
"mcpServers": {
"givemeanode": { "url": "https://mcp.givemeanode.com", "transport": "http" }
}
}In Capy, go to Settings, MCP servers, New MCP server, pick the HTTP transport, and enter the server URL:
https://mcp.givemeanode.comThen 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" }
}
}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" }
}
}In Zed's settings.json (zed: open settings from the command palette):
{
"context_servers": {
"givemeanode": { "url": "https://mcp.givemeanode.com" }
}
}Zed prompts for the OAuth sign-in on first use.
Make anyone a machine learning researcher
One sentence to your agent is the whole interface. The docs show every example as English, CLI, and the MCP calls underneath.
The full autoresearch suite
A full platform as a service designed and optimized for agents.
Interactive nodes
A container on an H100 with a persistent disk. Stop it and the files stay.
gman node create --chip h100 --wait
Batch jobs
Fire and forget. Queued time is free, checkpoints survive preemption.
gman job submit --chip h100 --context ./eval
Tasks
Thousands of work items, one container start. Lost machines cost only what was in flight.
gman job submit --tasks ./prompts.jsonl
Sweeps
Up to 256 variants of one job in a single call. One build, N runs.
gman api post /jobs/sweeps
Private networking
Your own nodes reaching each other over stable private addresses. Names resolve.
gman node create --network mesh1
Object storage
Org-owned buckets with a real S3 endpoint. Agents pull from them credential free.
gman storage cp ./train-data corpus/train/
Profiling
Locked clocks and unlocked profiler counters, set at create time and free.
create_node(chip: "8xh100", profiling: true)
Missions
Every job, log, and sample from one campaign gathered on a single page.
submit_job(mission: "trainer-v4")
Metrics
Active series per month, first ten thousand free.
Logs
Logs are the interface. Follow a detached command to exit.
gman logs tulip -f
Traces
Spans ingested per GB, the first 5 GB each month free.
Samples
One small file per step, appended to a timeline you can scroll through.
list_samples(job: "job-8x2mf")
RL sandboxes with ultra-fast forking and snapshots
Our agent sandboxes were built for RL, not inference. Load, fork, and snapshot in milliseconds so your GPUs spend more time humming.
Bake
Build the environment once and keep it as a snapshot. Baking bills as ordinary sandbox time.
create_sandbox_env(...)
Fork
One fork per sample, up to a thousand at once. Forking is free. 50ms per fork, 100ms per delete.
fork_sandbox(from, count)
Snapshot and branch
Capture a running sandbox without stopping it, then fork the branch point. Idle sandboxes park themselves. 150ms per snapshot, tens of ms to wake.
snapshot_sandbox(sbx)
Sandboxes pause automatically while your agent is thinking, to save you 7.5x
Sandboxes park after 1.5s idle and wake in tens of milliseconds. A 64-fork batch holding 2 GiB each across ten minutes of wall clock costs $0.98 held open the whole time and $0.13 with parking. Forks are free. The docs work through the arithmetic.
A new age of automated scientific discovery
Used by folks at
- Harvard
- MIT
- Stanford
- UC Berkeley
- UC San Diego
- UCLA
- University of Michigan
- UT Austin
“I LOVE givemeanode. I’ve been running astrophysics jobs on it. The agent-first design is amazing and the ticket experience has been remarkable.”
A fair queue nobody can buy out
We built a fair queue that lets folks buy a head start, but not the whole fleet. Everyone’s first node per hour gets a boost, so you will always get rapid experimentation.
Least served goes next
100 jobs from one lab do not put you 101st. They dispatch one, then hold GPUs, so you dispatch second.
Always priority for the little guy
Your first node or job per hour gets an advantage in the queue, regardless of who you are. Long live the experimenter.
A ceiling on the whole thing
Batch jobs never take more than 85% of the fleet, machines stay held back for wakes, and a returning owner is served before any new request at any price.
https://mcp.givemeanode.com