Content
[English](README-en.md)
---
# Partners
[](https://share.302.ai/mFS9MS)
[302.AI](https://share.302.ai/mFS9MS) is a pay-as-you-go AI application platform that offers the most comprehensive AI APIs and online applications available on the market.
* For users: We provide over 50 AI applications covering text, images, and audio/video across various fields, with no monthly fees and pay-per-use, available online.
* For developers: A one-stop access to almost all models and APIs needed for AI application development, with unified payment and integration.
* For enterprises: A separation of management and usage interfaces, allowing one person to manage while multiple users can utilize it, reducing the threshold and cost for small and medium-sized enterprises to use AI.
Try registering with GitHub for a one-click login [here](https://share.302.ai/mFS9MS)! Get a $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">In the flood of information (Feed), may you remain in Zen.</h3>
<p align="center">
zenfeed is your <strong>AI information hub</strong>. It serves as a <strong>smart RSS reader</strong>, a real-time <strong>"news" knowledge base</strong>, and can also act as your personal assistant to keep you updated on "designated events" and present <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]
> The description on DeepWiki is not entirely accurate.
---
**epub2rss**: Convert epub eBooks into an RSS Feed that updates one chapter daily, [join waitlist](https://epub2rss.pages.dev/)
**one-coffee**: A daily report product similar to syft, tracking everything (difference: supports podcasts and other modalities; high-quality sources, focusing on the AI field). Add me on WeChat below to join the waitlist.
---
**Sponsor the project to receive a Gemini Key**
<a href="https://afdian.com/a/glidea"><img src="docs/images/sponsor.png" width="500"></a>
<br/>
<a href="https://afdian.com/a/glidea">Sponsor the project to support development</a>
---
## 💡 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 summary form, facilitating quick access to information.
However, with the development of Web 2.0 and the rise of social media and algorithmic recommendations, RSS has not become mainstream. The closure of Google Reader in 2013 was a landmark event. As Zhang Yiming pointed out at the time, RSS requires users to have strong information filtering abilities and self-discipline to manage subscription sources; otherwise, they can easily be overwhelmed by information noise. He believed that for most users, a more effortless "personalized recommendation" is a better solution, which also gave rise to later platforms like Toutiao and Douyin.
Algorithmic recommendations do lower the threshold for information acquisition, but their excessive catering to human weaknesses often leads to information cocoons and entertainment addiction. If you want to obtain truly valuable content from the information flow, you need even stronger self-control to resist the algorithm's "feeding."
So, is pure RSS subscription the answer? Not necessarily. Information overload and filtering difficulties (information noise) remain pain points for RSS users.
Confucius advocated the doctrine of the mean. Can we find a compromise that allows us to enjoy the sense of control and high-quality sources brought by active RSS subscriptions while using technology to overcome the drawbacks of information overload?
Try zenfeed! **AI + RSS** might be a better way to acquire information in this era. zenfeed aims to leverage AI capabilities to help you automatically filter and summarize the information you care about, allowing you to maintain Zen in the flood of information (Feed).
> Reference article: [Can AI Revive RSS? - 少数派](https://sspai.com/post/89494)
---
## ✨ Features
**Designed for [RSS](https://zh.wikipedia.org/wiki/RSS) veterans** 🚗
* Your AI-powered RSS reader (to be used with [zenfeed-web](https://github.com/glidea/zenfeed-web))
* Can serve as an [MCP](https://mcp.so/) Server for [RSSHub](https://github.com/DIYgod/RSSHub)
* Customizable trusted RSS data sources to create a super-fast personal AI search engine
* Similar functionality 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 alternatives to [万物追踪](https://www.wwzzai.com/)** 🔍
* Powerful [information tracking capabilities](https://github.com/glidea/zenfeed/blob/main/docs/config-zh.md#%E8%B0%83%E5%BA%A6%E9%85%8D%E7%BD%AE-scheduls), with a greater emphasis on high-quality, customizable data sources
* Can serve as the RSS version of [AI Chief Intelligence Officer](https://github.com/TeamWiseFlow/wiseflow?tab=readme-ov-file), more flexible and closer to an 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 sufferers (like me)** 😌
* If you feel fatigued from frequently scrolling through information feeds, try the briefing feature. Receive AI briefings for specified time periods daily, allowing for efficient reading in one go, eliminating the hidden costs of context switching. Ah, it has a hint of Renaissance, doesn't it? ✨
* "zenfeed" is a combination of "zen" and "feed," meaning may you remain zen in the feed (information flood).
<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's [Relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config), zenfeed abstracts each piece of content into a set of tags, allowing you to process tags (scoring, classification, summarization, filtering, etc.) at each node of the pipeline through custom Prompts.
* **Flexible orchestration**: Based on the processed tags, 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 character. For details, see [Rewrite Rules](docs/tech/rewrite-zh.md).
* **Open APIs**:
* [Query API](/docs/query-api-zh.md)
* [RSS Exported API](/docs/rss-api-zh.md)
* [Notify Webhook](/docs/webhook-zh.md)
* A large number of declarative YAML configurations [docs/config-zh.md](https://github.com/glidea/zenfeed/blob/main/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 model services provided by [SiliconFlow](https://cloud.siliconflow.cn/) by default.
> * Models: `Qwen/Qwen3-8B` (free) and `Qwen/Qwen3-Embedding-4B`.
> * **!!! If you are willing to sponsor this project, you will receive a certain amount of Gemini 2.5 Pro/Flash!!! (see below)**
> * If you do not have a SiliconFlow account, using the [**invitation link**](https://cloud.siliconflow.cn/i/U2VS0Q5A) will grant you **14 yuan** in credits.
> * If you need to use other vendors or models, or require more detailed custom deployment, please refer to the [configuration documentation](https://github.com/glidea/zenfeed/blob/main/docs/config-zh.md) to edit `docker-compose.yml`.
### 2. One-click Deployment
> The service can be up in as little as 1 minute.
#### Mac / Linux
```bash
# Download the configuration file
curl -L -O https://raw.githubusercontent.com/glidea/zenfeed/main/docker-compose.yml
# Start the service (please replace your API_KEY)
API_KEY="sk-..." docker-compose -p zenfeed up -d
```
#### Windows (PowerShell)
```powershell
# Download the configuration file
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/glidea/zenfeed/main/docker-compose.yml" -OutFile "docker-compose.yml"
# Start the service (please replace your API_KEY)
$env:API_KEY = "sk-..."; docker-compose -p zenfeed up -d
```
🎉 **Deployment complete!**
Visit http://localhost:1400
> [!WARNING]
> * If deploying zenfeed in a public environment like a VPS, please access it via `http://<yourIP>:1400`, and ensure that the firewall/security group has allowed port `1400`.
> * **Security Tip:** zenfeed currently lacks an authentication mechanism, exposing the service to the public may leak your `API_KEY`. Please configure strict security group rules to allow access only from trusted IPs.
### 3. Getting Started
> Android version: https://github.com/xusonfan/zenfeedApp
#### Add RSS Sources
<img src="docs/images/web-add-source.png" alt="Add RSS source via web" width="400">
> * For migrating from Follow, please refer to [migrate-from-follow.md](docs/migrate-from-follow.md).
> * After adding, zenfeed needs to access the source site, please ensure the network is smooth.
> * Please wait a few minutes after adding for content fetching and processing, especially if the model has strict rate limits.
#### Configure Daily Briefings, Monitoring, etc.
<img src="docs/images/notification-with-web.png" alt="Configure notifications via web" width="400">
#### Configure MCP (Optional)
For example, configure MCP and connect to Zenfeed using Cherry Studio, see [Cherry Studio MCP](docs/cherry-studio-mcp.md).
> Default address `http://localhost:1301/sse`
#### More...
The page currently cannot express the powerful flexibility of zenfeed; for more features, please refer to the [configuration documentation](docs/config-zh.md).
---
## 🗺️ Roadmap
We have planned some cool features, feel free to check out the [Roadmap](/docs/roadmap-zh.md) and provide your suggestions!
---
## 💬 Communication and Support
> **For usage issues, please prioritize submitting an [Issue](https://github.com/glidea/zenfeed/issues)**, as this can help others with similar problems and better track and resolve issues.
<table>
<tr>
<td align="center">
<img src="docs/images/wechat.png" alt="Wechat QR Code" width="300">
<br>
<strong>Join the discussion group</strong>
</td>
<td align="center">
<img src="docs/images/sponsor.png" width="500">
<br>
<strong><a href="https://afdian.com/a/glidea">Buy me a bubble tea 🧋</a></strong>
</td>
</tr>
</table>
If you've made it this far, please give a **Star ⭐️**; it's my greatest motivation for ongoing maintenance!
Feel free to contact me for any interesting AI work!
---
## 📝 Notes and Disclaimers
### Notes
* **Version Compatibility:** API and configuration backward compatibility is not guaranteed for versions prior to 1.0.
* **Open Source License:** The project is licensed under AGPLv3, and any forks and distributions must remain open source.
* **Commercial Use:** Please contact the author for reporting commercial use, and support can be provided within reasonable limits. We welcome legitimate commercial use but do not support gray market activities using this project.
* **Data Storage:** Data will not be permanently stored, with a default retention of 8 days.
### Acknowledgments
* Thanks to [eryajf](https://github.com/eryajf) for the suggestion of [Compose Inline Config](https://github.com/glidea/zenfeed/issues/1), making deployment easier to understand.
* [](https://dartnode.com "Powered by DartNode - Free VPS for Open Source")
### Contributions Welcome
* Contribution guidelines are still being refined, but we adhere to a core principle: "Code style consistency."
### Disclaimer
<details>
<summary><strong>Click to expand and view the full disclaimer</strong></summary>
**Before using the `zenfeed` software (hereinafter referred to as "the software"), please read and understand this disclaimer carefully. Your downloading, installing, or using this software or any related services indicates that you have read, understood, and agreed to accept all terms of this statement. If you do not agree with any content of this statement, please stop using this software immediately.**
1. **Provided "as is":** This software is provided on an "as is" and "as available" basis, without any form of express or implied warranty. The project authors and contributors make no guarantees or representations regarding the merchantability, suitability for a particular purpose, non-infringement, accuracy, completeness, reliability, safety, timeliness, or performance of this software.
2. **User Responsibility:** You will bear full responsibility for all actions taken using this software. This includes but is not limited to:
* **Data Source Selection:** You are solely responsible for selecting and configuring the data sources (such as RSS feeds, and future possible Email sources) to be accessed. You must ensure that 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 this software to process, store, or distribute any illegal, infringing, defamatory, obscene, or otherwise objectionable content.
* **API Key and Credential Security:** You are responsible for protecting the security of any API keys, passwords, or other credentials configured in this software. The project authors and contributors are not responsible for any loss or damage resulting from your failure to safeguard them properly.
* **Configuration and Usage:** You are responsible for correctly configuring and using the features of this software, including content processing pipelines, filtering rules, notification settings, etc.
3. **Third-party Content and Services:** This software may integrate or rely on third-party data sources and services (such as RSSHub, LLM providers, SMTP service providers, etc.). The project authors and contributors are not responsible for the availability, accuracy, legality, safety, or terms of service of these third-party contents or services. Your interactions with these third parties are governed by their respective terms and policies. The copyright of any third-party content accessed or processed through this software (including original articles, summaries, classifications, ratings, etc.) belongs to the original rights holders, and you shall bear any legal responsibilities that may arise from using this content.
4. **No Guarantee of Content Processing:** This software uses technologies such as large language models (LLM) to process content (such as summarization, classification, scoring, 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 influenced by various factors and is not guaranteed.
5. **No Indirect or Consequential Damages:** Under no circumstances, regardless of the legal theory (contract, tort, or otherwise), shall the project authors and contributors be liable for any direct, indirect, incidental, special, punitive, or consequential damages arising from the use or inability to use this software, including but not limited to loss of profits, data loss, loss of goodwill, business interruption, or other commercial damages or losses, even if they have been advised of the possibility of such damages.
6. **Open Source Software:** This software is licensed under the AGPLv3 license. You are responsible for understanding and complying with the terms of that license.
7. **Not Legal Advice:** This disclaimer does not constitute legal advice. If you have any questions about the legal implications of using this 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 this software will be deemed acceptance of the modified terms.
**Please note again: Using this software to scrape, process, and distribute copyrighted content may pose legal risks. Users are responsible for ensuring that their usage complies with all applicable laws and regulations and the terms of service of third parties. The project authors and contributors bear no responsibility for any legal disputes or losses arising from user abuse or improper use of this software.**
</details>
