Show HN: Graph-based memory for local LLMs with multi-hop not just vector search

Category: ai-ml

Tags: knowledge-graph, llm-memory, reasoning, python, ai-agents, semantic-search

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

BrainAPI is a knowledge graph ecosystem that automatically extracts structured, time-aware relationships from raw text and documents, enabling explainable multi-hop reasoning for AI agents. It stands out by moving beyond vector similarity to provide traceable graph paths for queries, with a comprehensive ingestion pipeline and event-centric architecture.

Target audience: backend devs, data engineers, ai engineers

Repository: https://github.com/Lumen-Labs/brainapi2 · Python · NOASSERTION · 91 stars

View on Hacker News