Show HN: Local Search Agent – offline RAG, no embeddings, free tier

Category: infrastructure

Tags: rag, local-search, offline-ai, bm25, langgraph, document-retrieval

Score: 7.3/10 (Innovation: 6, Technical: 7, Documentation: 9, Utility: 7)

Local Search Agent is a Python framework that provides offline, local-file search and reasoning for AI agents using BM25 keyword search via Meilisearch, avoiding traditional RAG's embedding and vector database complexity. It is interesting for its deterministic, auditable retrieval approach and its comprehensive integration with LangGraph, including multi-tenant RBAC and OCR support for scanned PDFs.

Target audience: backend devs, data engineers, devops

Repository: https://github.com/wiss84/local-search-agent · Python · MIT · 2 stars

View on Hacker News