Xiangyue-Zhang/auto-deep-researcher-24x7

🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

About the project

Auto Deep Researcher 24x7 is an autonomous AI agent that runs and monitors deep learning experiments continuously. Researchers use it to automate experiment execution, including hyperparameter tuning and GPU or Slurm-based workloads. The catalogue add-ons provide agents, skills, and instructions for operating the experiment workflow.

1.3kStars on the repository

14Mods indexed here, across every type

3mo agoLast push, which is what freshness is scored on

Apache-2.0Licence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 7 mods

conf-search

Xiangyue-Zhang/auto-deep-researcher-24x7

Skill Codex

Search papers from top AI/ML conferences.

not rated 1.3k +2 3mo ago A SkillSpector: pass 11 tokens original Apache-2.0

daily-papers

Xiangyue-Zhang/auto-deep-researcher-24x7

Skill Codex

Daily arXiv paper recommendations with automatic deduplication.

not rated 1.3k +2 3mo ago A SkillSpector: pass 15 tokens original Apache-2.0

experiment-status

Xiangyue-Zhang/auto-deep-researcher-24x7

Skill Codex

Check status of running autonomous experiment loops.

not rated 1.3k +2 3mo ago A SkillSpector: pass 10 tokens original Apache-2.0

gpu-monitor

Xiangyue-Zhang/auto-deep-researcher-24x7

Skill Codex

Check GPU status, running experiments, and available resources.

not rated 1.3k +2 3mo ago A SkillSpector: pass 13 tokens original Apache-2.0

obsidian-sync

Xiangyue-Zhang/auto-deep-researcher-24x7

Skill Codex

Refresh Obsidian dashboard and daily notes from current experiment state.

not rated 1.3k +2 3mo ago A SkillSpector: pass 16 tokens original Apache-2.0

paper-analyze

Xiangyue-Zhang/auto-deep-researcher-24x7

Skill Codex

Deep analysis of a single paper with figure extraction from arXiv source.

not rated 1.3k +2 3mo ago A SkillSpector: pass 18 tokens original Apache-2.0

progress-report

Xiangyue-Zhang/auto-deep-researcher-24x7

Skill Codex

Generate structured research progress reports.

not rated 1.3k +2 3mo ago A SkillSpector: pass 8 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: