Show HN: Build queryable packs for AI agents from videos, podcasts, and files

Category: ai-ml

Tags: ai-agents, knowledge-retrieval, local-ai, mcp, rag

Score: 7.0/10 (Innovation: 7, Technical: 6, Documentation: 8, Utility: 7)

Beyin is a local-first engine that builds queryable knowledge packs from diverse sources (videos, podcasts, articles, files) for AI agents via the Model Context Protocol (MCP). It's interesting because it enables reusable, vendor-agnostic context retrieval across multiple AI agents while keeping all processing and data on the user's machine.

Target audience: backend devs, ai engineers, devops

Repository: https://github.com/buralog/beyin · Python · MIT

View on Hacker News