This project provides an AI-driven tool for aggregating RSS feeds, creating content, and automating workflows. It targets users who need to efficiently process information from various sources, translate and filter it, generate rich media content, and distribute it across platforms like WeChat and Feishu, or leverage AI agents for fully automated pipelines. The primary benefit is streamlining content curation and creation from RSS feeds using AI.

How It Works

AutoContents ingests standard RSS and RSSHub feeds, applying dual filtering (positive and blocklist keywords). It leverages large language models (LLMs) for AI translation and content generation, including creating cover images and copy with a Xiaohongshu-style preview. Content can be pushed to WeChat or saved to Feishu knowledge bases and multi-dimensional tables. A key feature is its Agent interface, exposing a full API that enables AI agents to automate the entire workflow, from news pulling and filtering to content creation and archiving, with built-in deduplication. Rendering uses Puppeteer for accurate image generation, supporting emojis and Chinese fonts.

Quick Start & Requirements

• Local Installation: Requires Node.js 20+. Optionally, a local RSSHub instance (defaults to http://localhost:1200). macOS users need Google Chrome installed for rendering. Clone the repository, copy the environment file (cp backend/.env.example backend/.env), and run ./start.sh for a one-click setup.
• Docker Deployment: Clone the repository, then run docker compose -p makecontent up -d --build.
• Access: Frontend: http://localhost:3711 (local), http://服务器IP:3710 (Docker). Backend API: http://localhost:3710/api (local).
• Configuration: Requires LLM API keys (OpenAI compatible), Feishu App ID/Secret, Space ID, and other platform-specific credentials.
• Links: Project Repository: https://github.com/comeonzhj/AutoContents. API Documentation: Skills/makecontents/references/api.md.

Highlighted Details

• AI-powered translation, filtering, and content generation from RSS feeds.
• Automated content creation with AI, including 1080x1440 cover images and descriptive copy.
• Multi-platform content distribution to WeChat (with a risk warning) and Feishu knowledge bases/multi-dimensional tables.
• Agent Skills integration for end-to-end automated content workflows.
• Comprehensive API for AI Agent interaction and workflow automation.
• Puppeteer-based rendering engine for high-fidelity image generation.

Maintenance & Community

The provided README does not detail specific community channels (e.g., Discord, Slack), notable contributors, sponsorships, or a public roadmap.

Licensing & Compatibility

The project is released under the MIT License, which generally permits commercial use and integration into closed-source projects.

Limitations & Caveats

Users are strongly advised against configuring the WeChat push feature due to potential account control risks. Direct posting to platforms like Xiaohongshu is also discouraged by the project itself, following official platform crackdowns; however, the tool supports manual publishing by allowing users to download all generated assets. LLM and Feishu integration requires obtaining and configuring external API keys and credentials.