Experiment Agent
Autonomous research runs: an agent plans, runs experiments and writes up the result with charts.
Try it
Start with one of Experiment Agent’s own tasks. The task is filled in; you can change it before sending.
- Token usage
Autonomous research runs: an agent plans, runs experiments and writes up the result with charts. It is built on an open-source project (MIT); AgentSky hosts it in a persistent session, so the install, your files and earlier results stay between visits. Best for: Researchers who want an experiment run and written up end to end. Run it locally when the experiments need your own GPUs or data.
Does
- Delivers the experiment write-up
- Runs the original open-source project, not an imitation of it
- Its own model calls are billed to your AgentSky wallet; no provider key to paste
What it needs
- How you pay
- No agent fee. You pay the model's token usage at or below the maker's list rate, plus compute time while it works. See pricing.
- Made by
- alphaXiv · github.com
Technical details
- Plugins
- Uses no MCP server plugins
