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.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/agents ./rig-auto-deep-researcher-24x7/agents $ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/skills ./rig-auto-deep-researcher-24x7/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/skills/auto-experiment .claude/skills/auto-experiment $ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/skills/conf-search .claude/skills/conf-search $ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/skills/daily-papers .claude/skills/daily-papers $ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/skills/experiment-status .claude/skills/experiment-status $ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/skills/gpu-monitor .claude/skills/gpu-monitor $ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/skills/obsidian-sync .claude/skills/obsidian-sync $ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/skills/paper-analyze .claude/skills/paper-analyze $ npx degit Xiangyue-Zhang/auto-deep-researcher-24x7/skills/progress-report .claude/skills/progress-report
$ curl -fsSL --create-dirs -o .claude/agents/code_agent.md https://raw.githubusercontent.com/Xiangyue-Zhang/auto-deep-researcher-24x7/main/agents/code_agent.md $ curl -fsSL --create-dirs -o .claude/agents/idea_agent.md https://raw.githubusercontent.com/Xiangyue-Zhang/auto-deep-researcher-24x7/main/agents/idea_agent.md $ curl -fsSL --create-dirs -o .claude/agents/leader.md https://raw.githubusercontent.com/Xiangyue-Zhang/auto-deep-researcher-24x7/main/agents/leader.md $ curl -fsSL --create-dirs -o .claude/agents/writing_agent.md https://raw.githubusercontent.com/Xiangyue-Zhang/auto-deep-researcher-24x7/main/agents/writing_agent.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (8)
auto-experimentconf-searchdaily-papersexperiment-statusgpu-monitorobsidian-syncpaper-analyzeprogress-report
Subagents (4)
| code_agent model: inherit | Experiment implementation, execution, and monitoring |
| idea_agent model: inherit | Literature search and hypothesis formation |
| leader model: inherit | Central decision-maker that plans experiments and reflects on results |
| writing_agent model: inherit | Report generation and paper writing |
Similar rigs
0xT4sty/claude-code-dotfiles
—
Pragmatist 979 tok ·
MyrskyDev/claude-agent-template
Multi-agent dev workflow template for Claude Code
Pragmatist 195 tok ·
jordimarsal/harness-standard
A standardized multi-agent harness for Opencode and Claude Code. Installs into any project with a single command.
Pragmatist 2.2k tok ·
ilang-ai/autocode
You say it. AutoCode ships it. 48 skills. Code to deployment in one session. I-Lang v5.0 judgment + secret-safe deploys. Free forever.
Skill Collector 1.6k tok ·