HN Showcase
Back to browse
GitHub Repository

A GraphRAG implementation with a Vocabulary system to optimise AI integration

4 starsTypeScript

Deep Memory – Vocabulary-driven graph memory for AI agents

by tjwheeler·Jun 9, 2026·4 points·2 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainNiche Gem

Vocabulary governance solves agent memory cold-start better than raw GraphRAG.

Strengths
  • •Schema validation before storage prevents inconsistent entity creation.
  • •Seven quickstart options including Neo4j, CosmosDB, and zero-setup in-memory.
  • •MCP server support means Claude Desktop integration without coding.
Weaknesses
  • •Graph memory for agents already has Mem0, LangChain, and other competitors.
  • •Zero stars and forks suggests untested in real production scenarios.
Category
AI/ML
Target Audience

AI agent developers, LLM application builders

Similar To

Mem0 · LangChain Memory · GraphRAG

Similar Projects

AI/ML●●Solid

Sovereign – Multi-agent OS with GraphRAG memory and HITL checkpoints

Runtime pause-and-resume checkpoints during execution plus per-agent escalation policies are a rare, practical safety feature — not just a pre-flight approval checkbox. The hybrid memory that scores vector similarity, BM25 keyword relevance, and entity/relation overlap together is a smart middle path between heavyweight graph DBs and plain vector stores. There's real engineering here (Docker compose, 55/55 tests, telemetry endpoints), though I'd like to see benchmarks and how the in-process GraphRAG scales versus external vector/graph services.

WizardryNiche Gem
borhensaidi
103mo ago
AI/ML●●Solid

Kremis – Deterministic memory graph for AI agents (Rust)

Deterministic graph memory vs. embeddings is clever, but fragmentation of AI memory ecosystems is already painful.

Big BrainWizardry
M2Dr3g0n
103mo ago