Content
[English](README-en.md)
---
# Partner
<a href="http://compshare.cn/?ytag=GPU_YY_JL_git_zenfeed">
<img src="docs/images/ucloud.png" alt="Thanks to UCloud for sponsoring this project" width="420">
</a>
Thanks to UCloud for sponsoring this project! UCloud is an AI cloud platform under UCloud, providing stable and comprehensive domestic and foreign model APIs, with just one key to call. The main package monthly, high-quality and affordable Coding Plan package, based on the official 2~5 fold discount. Support access to Claude Code, Codex and API calls. Support enterprise high concurrency, 7*24 technical support, self-service invoicing. Users who register through [this link](http://compshare.cn/?ytag=GPU_YY_JL_git_zenfeed) can get a free 5 yuan platform experience gold!
[](https://share.302.ai/mFS9MS)
[302.AI](https://share.302.ai/mFS9MS) is a pay-as-you-go AI application platform, providing the most comprehensive AI APIs and AI online applications on the market.
* For users: We provide more than 50 AI applications, covering text, image and audio/video fields, no monthly fee, pay-as-you-go, online use.
* For developers: One-stop access to almost all AI application development models and APIs needed, one-stop payment, unified access.
* For enterprises: Management and use interface separation, one person manages, multiple people use, reducing the threshold and cost of using AI for small and medium enterprises.
GitHub one-click login [Register one](https://share.302.ai/mFS9MS) and try it now! Get $1 credit immediately
---
# Main Content
<p align="center">
<img src="docs/images/crad.png" alt="zenfeed cover image">
</p>
<p align="center">
<a href="https://app.codacy.com/gh/glidea/zenfeed/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade"><img src="https://app.codacy.com/project/badge/Grade/1b51f1087558402d85496fbe7bddde89"/></a>
<a href="https://sonarcloud.io/summary/new_code?id=glidea_zenfeed"><img src="https://sonarcloud.io/api/project_badges/measure?project=glidea_zenfeed&metric=sqale_rating"/></a>
<a href="https://goreportcard.com/badge/github.com/glidea/zenfeed"><img src="https://goreportcard.com/badge/github.com/glidea/zenfeed"/></a>
<a href="https://deepwiki.com/glidea/zenfeed"><img src="https://deepwiki.com/badge.svg"/></a>
</p>
<h3 align="center">Stay Zen in the Feed</h3>
<p align="center">
zenfeed is your <strong>AI Information Hub</strong>. It is not only a <strong>smart RSS reader</strong>, but also a real-time <strong>"news" knowledge base</strong>, and can become your private secretary who helps you track "specified events" and presents <strong>analysis reports</strong>.
</p>
<p align="center">
<a href="https://zenfeed.xyz"><b>Online Experience (RSS reading only)</b></a>
|
<a href="https://github.com/xusonfan/zenfeedApp"><b>Android Experience (RSS reading only)</b></a>
|
<a href="docs/tech/hld-zh.md"><b>Technical Documentation</b></a>
|
<a href="#-Installation-and-Usage"><b>Quick Start</b></a>
</p>
> [!NOTE]
> DeepWiki's description is not entirely accurate
---
**epub2rss**: Convert epub e-books into daily updated RSS Feeds, [join waitlist](https://epub2rss.pages.dev/)
**one-coffee**: A daily report product similar to syft, tracking everything (difference: supports podcasts and multi-modal; high-quality sources, focusing on AI). Add me on WeChat to join the waitlist
---
## 💡 Preface
RSS (Really Simple Syndication) was born in the Web 1.0 era, aiming to solve the problem of information dispersion, allowing users to aggregate and track updates from multiple websites in one place, without frequent visits. It pushes website updates to subscribers in a summary form, making it easy to quickly obtain information.
However, with the development of Web 2.0 and the rise of social media and algorithm recommendations, RSS did not become mainstream. The closure of Google Reader in 2013 was a significant event. As Zhang Yiming pointed out at that time, RSS requires users to have strong information filtering capabilities and self-discipline to manage subscription sources, otherwise, it is easy to be overwhelmed by information noise. He believed that for most users, easier "personalized recommendations" are a better solution, which led to the emergence of Toutiao and Douyin.
Algorithm recommendations did indeed lower the threshold for information acquisition, but they often led to information cocoons and entertainment addiction. If you want to obtain truly valuable content from information streams, you need stronger self-control to resist the "feeding" of algorithms.
Is pure RSS subscription the answer? Not entirely. Information overload and screening difficulties (information noise) are still pain points for RSS users.
Confucius said that everything has a golden mean. Can we find a compromise that enjoys the control and high-quality sources brought by RSS active subscription, while using technical means to overcome its information overload drawbacks?
Try zenfeed! **AI + RSS**, perhaps a better information acquisition method for this era. zenfeed aims to utilize AI capabilities to automatically screen and summarize the information you care about, allowing you to stay Zen in the feed.
> Reference article: [AI Revives RSS? - Minority Report](https://sspai.com/post/89494)
---
## ✨ Features

**Designed for RSS veterans** 🚗
* Your AI-powered RSS reader (used with [zenfeed-web](https://github.com/glidea/zenfeed-web))
* Can be used as an [RSSHub](https://github.com/DIYgod/RSSHub) [MCP](https://mcp.so/) Server
* Customizable trusted RSS data sources, creating a super-fast personal AI search engine
* Features similar to [Feedly AI](https://feedly.com/ai)
<details>
<summary><b>Preview</b></summary>
<br>
<img src="docs/images/feed-list-with-web.png" alt="Feed list" width="600">
<img src="docs/images/chat-with-feeds.png" alt="Chat with feeds" width="500">
</details>
**Designed for seekers of [Universal Tracking](https://www.wwzzai.com/) alternatives** 🔍
* Possesses powerful [information tracking capabilities](https://github.com/glidea/zenfeed/blob/main/docs/config-zh.md#%E8%B0%83%E5%BA%A6%E9%85%8B%E7%BD%AE-scheduls), with an emphasis on high-quality, customizable data sources
* Can be used as an [AI Chief Intelligence Officer](https://github.com/TeamWiseFlow/wiseflow?tab=readme-ov-file) RSS version, more flexible and closer to engine form
<details>
<summary><b>Preview</b></summary>
<br>
<img src="docs/images/monitoring.png" alt="Monitoring setup" width="500">
<img src="docs/images/notification-with-web.png" alt="Notification example" width="500">
</details>
**Designed for Information Anxiety Disorder patients (like me)** 😌
* If you're tired of frequently browsing information streams, try the briefing feature. Receive daily AI briefings at designated times, efficiently reading in one go, and bid farewell to the hidden costs of context switching. Ah, it feels like a Renaissance! ✨
* "zenfeed" is a combination of "zen" and "feed", meaning to stay Zen in the feed.
<details>
<summary><b>Preview</b></summary>
<br>
<img src="docs/images/daily-brief.png" alt="Daily brief example" width="500">
</details>
**Designed for Developers** 🔬
* **Pipelined processing mechanism**: Similar to Prometheus' [Relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config), zenfeed abstracts each piece of content into a label set, allowing you to process (score, classify, summarize, filter, etc.) labels at each node of the pipeline with custom prompts.
* **Flexible orchestration**: Based on processed labels, you can freely query, filter, [route](https://github.com/glidea/zenfeed/blob/main/docs/config-zh.md#%E9%80%9A%E7%9F%A5%E8%B7%AF%E7%94%B1%E9%85%8D%E7%BD%AE-notifyroute-%E5%8F%8A-notifyroutesub_routes) and [notify](https://github.com/glidea/zenfeed/blob/main/docs/config-zh.md#%E9%80%9A%E7%9F%A5%E6%B8%A0%E9%81%93-email-%E9%85%8D%E7%BD%AE-notifychannelsemail), giving zenfeed a strong tool-like and personalized flavor. See [Rewrite Rules](docs/tech/rewrite-zh.md) for details.
* **Open API**:
* [Query API](/docs/query-api-zh.md)
* [RSS Exported API](/docs/rss-api-zh.md)
* [Notify Webhook](/docs/webhook-zh.md)
* [大量声明式 YAML 配置](/docs/config-zh.md)
<details>
<summary><b>Preview</b></summary>
<br>
<img src="docs/images/update-config-with-web.png" alt="Update config via web" width="500">
</details>
<p align="center">
<a href="docs/preview.md"><b>➡️ View more effect previews</b></a>
</p>
---
## 🚀 Installation and Usage
### 1. Preparation
> [!IMPORTANT]
> zenfeed uses [Silicon Flow](https://cloud.siliconflow.cn/) provided model services by default.
> * Models: `Qwen/Qwen3-8B` (free) and `Qwen/Qwen3-Embedding-4B`.
> * **!!!If you are willing to sponsor this project, you will be gifted a certain amount of Gemini 2.5 Pro/Flash!!! (see below)**
> * If you don't have a Silicon Flow account, use [**invitation link**](https://cloud.siliconflow.cn/i/U2VS0Q5A) to get **14 yuan** credit.
> * If you need to use other vendors or models, or perform more detailed custom deployment, please refer to [configuration documentation](https://github.com/glidea/zenfeed/blob/main/docs/config-zh.md) to edit `docker-compose.yml`.
### 2. One-click Deployment
> Fastest 1 minute to start the service.
#### Mac / Linux
```bash
# Download configuration file
curl -L -O https://raw.githubusercontent.com/glidea/zenfeed/main/docker-compose.yml
# Start service (please replace your API_KEY)
API_KEY="sk-..." docker-compose -p zenfeed up -d
```
#### Windows (PowerShell)
```powershell
# Download configuration file
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/glidea/zenfeed/main/docker-compose.yml" -OutFile "docker-compose.yml"
# Start service (please replace your API_KEY)
$env:API_KEY = "sk-..."; docker-compose -p zenfeed up -d
```
🎉 **Deployment completed!**
Access http://localhost:1400
> [!WARNING]
> * If you deploy zenfeed on VPS or public network environment, please access via `http://<your IP>:1400` and ensure the firewall/security group has opened port `1400`.
> * **Security tip:** zenfeed has no authentication mechanism yet, exposing the service to the public network may leak your `API_KEY`. Please configure strict security group rules to only open access to trusted IPs.
### 3. Getting Started
> Android: https://github.com/xusonfan/zenfeedApp
#### Add RSS subscription source
<img src="docs/images/web-add-source.png" alt="Add RSS source via web" width="400">
> * Migration from Follow, please refer to [migrate-from-follow.md](docs/migrate-from-follow.md).
> * After adding, zenfeed needs to access the source station, please ensure the network is smooth.
> * After adding, please wait a few minutes for content capture and processing, especially when the model has strict rate limits.
#### Configure daily briefing, monitoring, etc.
<img src="docs/images/notification-with-web.png" alt="Configure notifications via web" width="400">
#### Configure MCP (optional)
Using Cherry Studio as an example, configure MCP and connect to Zenfeed, see [Cherry Studio MCP](docs/cherry-studio-mcp.md).
> Default address `http://localhost:1301/sse`
#### More...
The page cannot fully express zenfeed's powerful flexibility. For more gameplay, please refer to [configuration documentation](docs/config-zh.md)
---
## 🗺️ Roadmap
We plan some cool features, welcome to view [Roadmap](/docs/roadmap-zh.md) and propose your suggestions!
---
## 💬 Communication and Support
> **Please propose issues in [Issues](https://github.com/glidea/zenfeed/issues) first, which can help friends with similar problems and track and solve problems better.**
<table>
<tr>
<td align="center">
<img src="https://github.com/glidea/zenfeed/blob/main/docs/images/wechat.png?raw=true" alt="Wechat QR Code" width="300">
<br>
<strong>AI Learning Exchange Community</strong>
</td>
<td align="center">
<img src="https://github.com/glidea/banana-prompt-quicker/blob/main/images/glidea.png?raw=true" width="250">
<br>
<strong><a href="https://glidea.zenfeed.xyz/">My other projects</a></strong>
</td>
</tr>
<tr>
<td align="center" colspan="2">
<img src="https://github.com/glidea/banana-prompt-quicker/blob/main/images/readnote.png?raw=true" width="400">
<br>
<strong><a href="https://www.xiaohongshu.com/user/profile/5f7dc54d0000000001004afb">📕 Xiaohongshu account - Continuously sharing AI original content</a></strong>
</td>
</tr>
</table>
You see here, help me star ⭐️, this is the greatest motivation for me to maintain!
If you have interesting AI jobs, please contact me!
---
## 📝 Notes and Disclaimer
### Notes
* **Version compatibility:** Before version 1.0, API and configuration backward compatibility is not guaranteed.
* **Open-source protocol:** The project adopts AGPLv3 protocol, any fork and distribution must keep open source.
* **Commercial use:** Please contact the author for commercial use, support can be provided within a reasonable range. We welcome legitimate commercial use and discourage using this project for gray industries.
* **Data storage:** Data will not be stored permanently, default storage for 8 days.
### Thanks
* Thanks to [eryajf](https://github.com/eryajf) for providing [Compose Inline Config](https://github.com/glidea/zenfeed/issues/1) suggestions, making deployment easier to understand.
* [](https://dartnode.com "Powered by DartNode - Free VPS for Open Source")
### Welcome to contribute
* The contribution specification is being improved, but we adhere to a core principle: "code style consistency".
### Disclaimer
<details>
<summary><strong>Click to view full disclaimer</strong></summary>
**Before using the `zenfeed` software (hereinafter referred to as "the Software"), please carefully read and understand this disclaimer. Your download, installation, or use of the Software or any related services constitutes your reading, understanding, and agreement to all terms of this statement. If you do not agree with any content of this statement, please immediately stop using the Software.**
1. **"As-Is" Provision:** The Software is provided "as-is" and "as-available" without any express or implied warranties of any kind. The project authors and contributors make no guarantees or representations regarding the merchantability, fitness for a particular purpose, non-infringement, accuracy, completeness, reliability, security, timeliness, or performance of the Software.
2. **User Responsibilities:** You will be solely responsible for all actions related to the use of the Software, including but not limited to:
* **Data Source Selection:** You are responsible for selecting and configuring the data sources to be accessed (such as RSS feeds, potential future Email sources, etc.). You must ensure you have the right to access and process the content of these data sources and comply with their respective terms of service, copyright policies, and relevant laws and regulations.
* **Content Compliance:** You must not use the Software to process, store, or distribute any illegal, infringing, defamatory, obscene, or otherwise objectionable content.
* **API Keys and Credentials Security:** You are responsible for protecting the security of any API keys, passwords, or other credentials configured in the Software. The project authors and contributors will not be liable for any losses or damages caused by your failure to properly secure these.
* **Configuration and Use:** You are responsible for correctly configuring and using the features of the Software, including content processing pipelines, filtering rules, notification settings, etc.
3. **Third-Party Content and Services:** The Software may integrate or depend on third-party data sources or services (such as RSSHub, LLM providers, SMTP service providers, etc.). The project authors and contributors are not responsible for the availability, accuracy, legality, security, or terms of service of these third-party content or services. Your interaction with these third parties is subject to their respective terms and policies. The copyright of third-party content accessed or processed through the Software (including original articles, summaries, classifications, ratings, etc.) belongs to the original copyright holders, and you should bear the legal responsibilities that may arise from using these content.
4. **No Content Processing Guarantee:** The Software uses large language models (LLM) and other technologies to process content (such as summaries, classifications, ratings, filtering). These processing results may be inaccurate, incomplete, or biased. The project authors and contributors are not responsible for any decisions or actions taken based on these processing results. The accuracy of semantic search results is also affected by various factors and is not guaranteed.
5. **No Indirect or Consequential Damages:** In no event will the project authors and contributors be liable for any direct, indirect, incidental, special, punitive, or consequential damages arising out of or in connection with the use or inability to use the Software, whether in contract, tort, or otherwise, including but not limited to loss of profits, data loss, loss of goodwill, business interruption, or other commercial damages or losses, even if advised of the possibility of such damages.
6. **Open Source Software:** The Software is licensed under the AGPLv3 license. You are responsible for understanding and complying with the terms of this license.
7. **Not Legal Advice:** This disclaimer does not constitute legal advice. If you have any questions about the legal implications of using the Software, you should consult a qualified legal professional.
8. **Modification and Acceptance:** The project authors reserve the right to modify this disclaimer at any time. Continued use of the Software will be deemed acceptance of the modified terms.
**Please note again: Using the Software to crawl, process, and distribute copyrighted content may involve legal risks. Users are responsible for ensuring that their use complies with all applicable laws and regulations and third-party service terms. The project authors and contributors will not be liable for any legal disputes or losses caused by users' abuse or improper use of the Software.**
</details>
MCP Config
Below is the configuration for this MCP Server. You can copy it directly to Cursor or other MCP clients.
mcp.json
Connection Info
You Might Also Like
awesome-mcp-servers
A collection of MCP servers.
servers
Model Context Protocol Servers
servers
Model Context Protocol Servers
mcphub.nvim
mcphub.nvim is an intelligent terminal for enhanced MCP server management.
Claude-Code-Everything-You-Need-to-Know
A comprehensive guide to mastering Claude Code with tutorials and strategies.
headroom
The Context Optimization Layer for LLM Applications