auto-deep-researcher-24x7

Agent that runs deep learning experiments around the clock on local, SSH or Slurm backends and records each outcome

Agent by Xiangyue-Zhang

IndexedApache-2.0★ 1,136

Write a review

Get started

Setup steps are in the repository. Website · Repository

About

The agent plans experiments, runs them and monitors the jobs until they finish, then writes each cycle's hypothesis, metrics and outcome to an experiment ledger that feeds later planning. It supports local, SSH and Slurm execution, and on Slurm it reads final job states from sacct. It works with Claude and Codex subscriptions, or with DeepSeek, Qwen, Kimi and GLM through OpenAI-compatible APIs.

Use cases: research, workflow-automation, code-generation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: researchREADME
Autonomy: Autonomous: runs tasks end to end and reports backREADME
Where you use it: TerminalREADME
Hosting: You run itREADME
Models: anthropic, openai, deepseek, qwen, kimi, glmREADME
Open source: YesREADME

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Signals

Stars: 1,136
Forks: 95
Open issues: 13
Last commit: Jun 3, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/Xiangyue-Zhang/auto-deep-researcher-24x7
Website: arxiv.org/abs/2604.05854
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

More from Xiangyue-Zhang

Cite this page

auto-deep-researcher-24x7. Agent Mart. https://agentmart.dev/agents/auto-deep-researcher-24x7 (last updated 2026-10-24)