← Back to Product Feed

GitHub Open Source wanshuiyin/Auto-claude-code-research-in-sleep

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

3,359
Traction Score
284
Forks
Mar 10, 2026
Launch Date
View Origin Link

Product Positioning & Context

AI Executive Synthesis
Enabling seamless, bidirectional communication and interaction between ARIS (using Claude Code) and enterprise collaboration platforms like Feishu, supporting 'autonomous ML research' within existing workflows.
This issue highlights a critical failure in ARIS's integration with Feishu (飞书) when operating in bidirectional interactive mode. While messages are received, the system fails to generate replies, rendering the interactive functionality broken. This directly impedes ARIS's ability to facilitate 'autonomous ML research' within enterprise communication platforms, as real-time feedback and collaborative loops are essential. The distinction between functional 'push mode' and broken 'bidirectional interactive mode' points to a specific flaw in the response generation or delivery mechanism within the interactive setup. This significantly limits ARIS's utility for teams relying on Feishu for collaborative agent-driven workflows.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
ai-research ai-tools aris autonomous-agent claude claude-code claude-code-skills codex

Related Ecosystem & Alternatives

Discover adjacent products, open-source repositories, and developer tools sharing similar technical architecture.

Deep-Dive FAQs

What is wanshuiyin/Auto-claude-code-research-in-sleep?
wanshuiyin/Auto-claude-code-research-in-sleep is analyzed by our AI as: Enabling seamless, bidirectional communication and interaction between ARIS (using Claude Code) and enterprise collaboration platforms like Feishu, supporting 'autonomous ML research' within existing workflows.. It focuses on This issue highlights a critical failure in ARIS's integration with Feishu (飞书) when operating in bidirectional interactive mode. While messages ...
Where did wanshuiyin/Auto-claude-code-research-in-sleep originate?
Data for wanshuiyin/Auto-claude-code-research-in-sleep was aggregated directly from the GitHub Open Source community ecosystem, representing raw developer and early-adopter sentiment.
When was wanshuiyin/Auto-claude-code-research-in-sleep publicly launched?
The initial public indexing or launch date for wanshuiyin/Auto-claude-code-research-in-sleep within our tracked developer communities was recorded on March 10, 2026.
How popular is wanshuiyin/Auto-claude-code-research-in-sleep?
wanshuiyin/Auto-claude-code-research-in-sleep has achieved measurable traction, logging over 3,359 traction score and facilitating 284 recorded discussions or engagements.
Which technical categories define wanshuiyin/Auto-claude-code-research-in-sleep?
Based on metadata extraction, wanshuiyin/Auto-claude-code-research-in-sleep is categorized under topics such as: ai-research, ai-tools, aris, autonomous-agent.
Are there active development issues for wanshuiyin/Auto-claude-code-research-in-sleep?
Yes, we are currently tracking open architectural debates and bug reports for this project on GitHub. There are currently 5 active high-priority issues logged recently.
What are some commercial alternatives to wanshuiyin/Auto-claude-code-research-in-sleep?
Our semantic intelligence engine identifies potential commercial alternatives in the SaaS space, such as Databerry, which offers overlapping value propositions.
How does the creator describe wanshuiyin/Auto-claude-code-research-in-sleep?
The original author or development team describes the product as follows: "ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works..."

Active Developer Issues (GitHub)

open Add a description to improve Dispatch discoverability
Logged: Mar 29, 2026
open 请问有没有预期的大概token消耗量,比如跑一晚上大约会用掉多少token
Logged: Mar 25, 2026
open mcp codex连不上的情况
Logged: Mar 24, 2026
open research-lit这一步websearch有点问题
Logged: Mar 23, 2026
open llm-chat MCP: add auto-fallback on 504 Gateway Timeout
Logged: Mar 22, 2026

Community Voice & Feedback

heartInsert • Apr 13, 2026
可能还是得人为参与,肯定还是有幻觉。还得发展2年。
tianming23 • Apr 11, 2026
好奇,这个项目真的可以拿下a会吗?
wanshuiyin • Apr 1, 2026
这个 400 错误是 Codex 账户类型限制导致的,不是 ARIS 的问题:

> The 'gpt-5.4-xhigh' model is not supported when using Codex with a ChatGPT account.

**原因**:ChatGPT Plus 订阅的 Codex 对可用模型有限制,部分高端模型(gpt-5.4)可能不在支持列表中。

**解决方案**:
1. **检查 Codex 支持的模型列表**:运行 `codex` 看可用模型
2. **如果 gpt-5.4 不可用**,可以在 skill 中手动指定较低的模型(如 `o3`)
3. **或者用 llm-chat MCP 替代**:通过 OpenAI API key 直连(不经 Codex),支持所有模型。详见 `mcp-servers/llm-chat/`,同时可用 `tools/convert_skills_to_llm_chat.py` 自动转换所有 skill

如果还有问题欢迎重新开 issue。
xilinQAQ • Mar 28, 2026
> > > 有时会出现codex返回400错误代码的情况,然后一路从5.4降到4o,最后不显示模型了,那最后用的什么模型呢?  
> > > > Error: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-5.4-xhigh' model is not supported when using Codex with
> > > > a ChatGPT account."}}
> > >
> > >
> > > > Error: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-4o' model is not supported when using Codex with a
> > > > ChatGPT account."}}
> > >
> > >
> > > 因为tz的问题吗?有大佬遇到过类似情况么。
> >
> >
> > 请问开了GPT plus 嘛~ 我今天晚上用还是好的诶
>
> 开了的大佬,网页版能正常用。直接问了claude,破案了😂
>
> > 配置确实是 model = "gpt-5.4"。
> > 问题出在我第一次调用时手动指定了 model: "gpt-5.4-xhigh"(带 -xhigh 后缀),这不是一个合法的模型ID,所以报错。后续又试了 o3、gpt-4o,同样不被 ChatGPT
> > 账户支持。
> > 最后成功的调用没有传 model 参数,于是 Codex 用了配置文件里的默认值 gpt-5.4,这才走通了。
> > 总结:你的配置没问题,是我的错——不该手动覆盖 model 参数,应该让它走默认配置。后续调用我会直接用默认的 gpt-5.4。

你的这个model = "gpt-5.4",是在哪里改的,我这个自动跳gpt5.2
jinyiyexings • Mar 25, 2026
> > 有时会出现codex返回400错误代码的情况,然后一路从5.4降到4o,最后不显示模型了,那最后用的什么模型呢?  
> > > Error: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-5.4-xhigh' model is not supported when using Codex with
> > > a ChatGPT account."}}
> >
> >
> > > Error: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-4o' model is not supported when using Codex with a
> > > ChatGPT account."}}
> >
> >
> > 因为tz的问题吗?有大佬遇到过类似情况么。
>
> 请问开了GPT plus 嘛~ 我今天晚上用还是好的诶

开了的大佬,网页版能正常用。直接问了claude,破案了😂

> 配置确实是 model = "gpt-5.4"。
>
> 问题出在我第一次调用时手动指定了 model: "gpt-5.4-xhigh"(带 -xhigh 后缀),这不是一个合法的模型ID,所以报错。后续又试了 o3、gpt-4o,同样不被 ChatGPT
> 账户支持。
>
> 最后成功的调用没有传 model 参数,于是 Codex 用了配置文件里的默认值 gpt-5.4,这才走通了。
>
> 总结:你的配置没问题,是我的错——不该手动覆盖 model 参数,应该让它走默认配置。后续调用我会直接用默认的 gpt-5.4。
wanshuiyin • Mar 24, 2026
> 有时会出现codex返回400错误代码的情况,然后一路从5.4降到4o,最后不显示模型了,那最后用的什么模型呢?  
>
> > Error: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-5.4-xhigh' model is not supported when using Codex with
> > a ChatGPT account."}}
>
> > Error: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-4o' model is not supported when using Codex with a
> > ChatGPT account."}}
>
> 因为tz的问题吗?有大佬遇到过类似情况么。

请问开了GPT plus 嘛~ 我今天晚上用还是好的诶
nblvguohao • Mar 21, 2026
一样的情况,不稳定
wanshuiyin • Mar 20, 2026
> > > No description provided.
> >
> >
> > 现在已经适配Cursor 和单独一个Codex Subagent review,欢迎体验~
>
> 出现代码问题时,能否让他把问题写进code_guide.md文件,然后等待人接入,如果一段时间没人介入就自动cli端修复,因为用的glm5,写代码不是很强,我现在是这样做的,然后让侧栏的codex去根据code_guide修代码

这个我找时间适配一下
Radar-Lei • Mar 18, 2026
我opus 4.6 + gpt 5.4 xhigh fast

/research-pipeline — AUTO_PROCEED: true 也会断
churoc • Mar 18, 2026
> > No description provided.
>
> 现在已经适配Cursor 和单独一个Codex Subagent review,欢迎体验~

出现代码问题时,能否让他把问题写进code_guide.md文件,然后等待人接入,如果一段时间没人介入就自动cli端修复,因为用的glm5,写代码不是很强,我现在是这样做的,然后让侧栏的codex去根据code_guide修代码
shed-e • Mar 18, 2026
同样的问题,执行到一半就停了
wanshuiyin • Mar 18, 2026
> No description provided.

现在已经适配Cursor 和单独一个Codex Subagent review,欢迎体验~
ngyygm • Mar 17, 2026
wanshuiyin • Mar 17, 2026
> No description provided.

我们即将给一个md 文档描述怎么适配,但是现在git仓库有点问题,不能fork 请稍等
QiNing110 • Mar 15, 2026
**桥接输出如下图,没有显示received message之类的日志,
同时也没有/path/to/feishu-claude-code/logs/*.log这一路径**

Discovery Source

GitHub Open Source GitHub Open Source

Aggregated via automated community intelligence tracking.

Tech Stack Dependencies

No direct open-source NPM package mentions detected in the product documentation.

Media Tractions & Mentions

No mainstream media stories specifically mentioning this product name have been intercepted yet.

Deep Research & Science

No direct peer-reviewed scientific literature matched with this product's architecture.