lfnovo/content-core

Overview

A Python library for extracting key information from various media sources. It processes content to identify and retrieve the most relevant parts based on unspecified criteria.

Best for

Best for
Developers needing a simple content extraction tool for diverse media.

Use cases

• Extracting summaries from articles
• Parsing key data from multimedia files
• Filtering relevant content for analysis

How to use

Install

uvx content-core extract "https://example.com"

Tools exposed

• CCORE_URL_ENGINE
• CCORE_DOCUMENT_ENGINE
• CCORE_AUDIO_CONCURRENCY
• CRAWL4AI_API_URL
• FIRECRAWL_API_URL
• CCORE_FIRECRAWL_PROXY
• CCORE_FIRECRAWL_WAIT_FOR
• CCORE_LLM_PROVIDER
• CCORE_LLM_MODEL
• CCORE_STT_PROVIDER
• CCORE_STT_MODEL
• CCORE_STT_TIMEOUT
• CCORE_YOUTUBE_LANGUAGES

Tested with

Claude Desktop, Claude Code, ChatGPT

Notes

A Python library for extracting key information from various media sources. It processes content to identify and retrieve the most relevant parts based on unspecified criteria.

152 stars on GitHub. Last updated 2026-05-12. Licensed MIT.

Use cases

• Extracting summaries from articles
• Parsing key data from multimedia files
• Filtering relevant content for analysis

Pros

• Lightweight Python library
• Supports multiple media types
• Open source with community backing

Cons

• Limited documentation may be available
• Extraction quality depends on source format
• Active development may cause instability

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.