Skip to main content
Are you a large language model? This page is available as raw markdown at /autoresearch.md. The full docset is at /llms-full.md and the index is at /llms.md.

Autoresearch

C3 runs your research loop remotely. A research engine proposes changes to a program, evaluates them on C3 compute, and keeps the measured results. Submit from Python, close your notebook, and return to the same run when you want to inspect its progress.

Start with a short GPU experiment. It includes a working candidate and evaluator, so you can see a complete run before adapting it to your own research.

What a run contains

PartWhat you choose or supply
Research engineOpenEvolve is the first supported engine.
Language modelsA model or weighted model ensemble served through OpenRouter.
ComputeA C3 hardware profile and, optionally, a particular compute provider.
CandidateThe initial Python program that the engine will try to improve.
EvaluatorA Python function that measures each candidate and returns a score.
LimitsCampaign duration, evaluation duration, number of evaluations, and an optional budget.

The engine coordinates the loop while C3 handles GPU provisioning, job execution, logs, artifacts, access control and credits. The dashboard records the selected engine, models and compute configuration alongside the run. OpenEvolve is an engine choice, not the name of the C3 product; additional engines are not yet implemented.

Follow the experiment

Each submission returns a durable ID and a private /squeue/ar_… link. The Autoresearch section of the dashboard, directly above Jobs, lists your runs. A run's overview diagram shows its planned loop and current phase; the details show individual evaluations, scores, compute jobs and saved outputs.

Current availability

Autoresearch is a staging pilot. Use the supplied pilot source revision, a C3 staging API key and account credits. Its API is https://test.api.cthree.cloud and its dashboard is the staging Autoresearch page. The Python SDK is installed from that source revision; these instructions do not assume a public package release.

The pilot supports OpenEvolve 0.2.26, sequential evaluations and one active campaign across the deployment. A crashed controller does not automatically resume. Completed progress and artifacts remain available. Production CLI and MCP submission of research campaigns are not enabled.