Top AI Repos β open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
π₯ An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
| Date | Stars |
|---|---|
| 2026-07-24 | 1222 |
| 2026-07-25 | 1224 |
| 2026-07-28 | 1224 |
| 2026-07-30 | 1224 |
| 2026-07-31 | 1226 |
| 2026-08-06 | 1255 |
Today
+29 stars today
This week
+31 stars this week
This month
β stars this month
Momentum
132.0
growth rate 2.53%/day
<p align="center">
<img src="assets/banner.png" alt="Deep Researcher Agent" width="700"/>
</p>
<h1 align="center">Deep Researcher Agent</h1>
<h3 align="center">24/7 Autonomous Deep Learning Experiment Agent</h3>
<p align="center">
<strong>An AI agent that autonomously runs your deep learning experiments 24/7 while you sleep.</strong>
</p>
<p align="center">
<a href="README.md">English</a> |
<a href="docs/README_CN.md">δΈζ</a> |
<a href="docs/README_JP.md">ζ₯ζ¬θͺ</a> |
<a href="docs/README_KR.md">νκ΅μ΄</a>
</p>
<p align="center">
<a href="#quickstart"><img src="https://img.shields.io/badge/-Quick_Start-blue?style=for-the-badge" alt="Quick Start"/></a>
<a href="docs/architecture.md"><img src="https://img.shields.io/badge/-Architecture-orange?style=for-the-badge" alt="Architecture"/></a>
</p>
<p align="center">
<img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="Python"/>
<img src="https://img.shields.io/badge/Claude_Code-compatible-blueviolet.svg" alt="Claude Code"/>
<img src="https://img.shields.io/badge/Codex_CLI-compatible-green.svg" alt="Codex CLI"/>
<img src="https://img.shields.io/badge/license-Apache_2.0-green.svg" alt="License"/>
<a href="https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7/stargazers"><img src="https://img.shields.io/github/stars/Xiangyue-Zhang/auto-deep-researcher-24x7?color=yellow&logo=github&label=Stars" alt="Stars"/></a>
</p>
<p align="center">
<a href="https://arxiv.org/abs/2604.05854"><img src="https://img.shields.io/badge/Technical%20Report-2604.05854-b31b1b.svg" alt="Technical Report"/></a>
</p>
---
## Recent Updates
**2026-06-03 β 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 β `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 β no new dependency.
(`core/agents.py`)
```yaml
agent:
provider: "deepseek" # or qwen / kimi / glm
model: "deepseek-chat" # vendor's model id
```
**2026-06-02 β Slurm execution backend + truthful experiment outcomes**
- **Slurm execution backend** β 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 β **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 β without ever reaping a job `sacct` still reports as queued
or running. File and repo-reading ops reuse the SSH path (the login node shares
the NFS workspace). (`core/execution.py`)
- **Truthful experiment outcomes** β the monitor now asks the backend for a
finished job's real terminal state via `final_status()`, so a `FAILED` /
`TIMEOUT` / `CANCELLED` run is no longer silently recorded as `completed`. The
outcome flows into `state.json`, the experiment ledger, and the REFLECT
context, so the agent reasons over what actually happened. On Slurm the state
comes from `sacct`; pid-only backends (`local`/`ssh`) report it as
indeterminate and keep prior behavior. (`core/monitor.py`, `core/loop.py`)
- Additive and opt-in; `local`/`ssh` behavior is unchanged. (+21 unit tests, no
cluster required.)
**2026-06-01 β v2.0 (major update)**
Excerpt of 43,139 characters
Read on GitHub
20
Would you bet a product on this? Bounded 0β100 and slow moving.
matched fp:229323720ee251dd, topic:ai-agent, topic:llm-agent, desc:ai agent
matched fp:229323720ee251dd, topic:deep-learning, topic:pytorch