{"repo":"Xiangyue-Zhang/auto-deep-researcher-24x7","free":true,"listed":false,"github":"https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7","clone":"git clone https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7.git","description":"🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.","language":"Python","stars":1276,"topics":["ai-agent","autonomous-agent","claude-code","deep-learning","experiment-automation","gpu","hyperparameter-tuning","llm-agent","machine-learning","mlops"],"license":"Apache-2.0","category":"machine-learning","readme_excerpt":"Deep Researcher Agent 24/7 Autonomous Deep Learning Experiment Agent An AI agent that autonomously runs your deep learning experiments 24/7 while you sleep. English 中文 日本語 한국어 --- Recent Updates 2026-06-03 — Domestic LLM API presets - Run the agent on a Chinese LLM API instead of a Claude/Codex subscription by setting agent.provider to a one-word preset — deepseek , qwen ( dashscope ), kimi ( moonshot ), or glm ( zhipu ). The preset auto-fills the OpenAI-compatible base url and the default key env ( DEEPSEEK API KEY / DASHSCOPE API KEY / MOONSHOT API KEY / ZHIPUAI API KEY ); you just set model to that vendor's model id. base url / api key env stay overridable for self-hosted or proxied endpoints. This is a thin alias over the existing OpenAI-compatible path — no new dependency. ( core/agents.py ) 2026-06-02 — Slurm execution backend + truthful experiment outcomes - Slurm execution backend — added execution.mode: \"slurm\" so the agent can drive experiments on a Slurm cluster. The controller stays local; training is submitted to the login node with sbatch --parsable over a single transient SSH call that exits immediately — no process is ever left running on the login node . sacct is the sole liveness authority (Slurm enforces --time ), GPU status is read from the partition's squeue occupancy, and two bounds inside the liveness check (consecutive-unknown grace + a --time -derived wall-clock backstop) guarantee the monitor loop terminates even if the cluster goes unreachable — wit","default_branch":null,"files":null,"tree":[],"storefront":"/r/Xiangyue-Zhang","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Xiangyue-Zhang/auto-deep-researcher-24x7/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}