HN Showcase
Back to browse
GitHub Repository

Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-weighted RRF. Apache-2.0.

25 starsPython

Magpie-search, Federated, local-first search for an AI

by VektorGeist·Jul 9, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainNiche Gem

Trust-weighted RRF fusion across five sources with fact > reference > lead > stale tiers.

Strengths
  • •Trust-tier ranking (fact > reference > lead > stale) adds verifiability missing from typical RAG
  • •Local-first with SQLite FTS5 + sqlite-vec means no server dependencies or telemetry
  • •MCP integration lets agents query all sources through a single standardized interface
Weaknesses
  • •AI agent search is crowded with Cursor, Continue, and dozens of RAG tools already
  • •Only 25 stars suggests limited real-world testing or adoption so far
Category
AI/ML
Target Audience

AI agent developers, LLM application builders

Similar To

LangChain · LlamaIndex · Sourcegraph Cody

Post Description

Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-weighted RRF.

Similar Projects

AI/ML●●Solid

Magpie-Search

Trust-tier ranking beats naive RAG fusion when sources conflict.

Big BrainNiche Gem
Floukie
2016d ago
Data●●Solid

Vector databases are the wrong primitive for AI agents

Knowledge graphs beat vector similarity for structured relationship queries.

Big BrainBold Bet
ajainvivek
113mo ago