HN Showcase
Back to browse
GitHub Repository

The Open-Source AI Memory Layer

6 starsTypeScript

Aethene – Open-source AI memory layer

by akhilponnada·Feb 22, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemShip It

Memory deduplication and contradiction detection, but vector DBs already do semantic search.

Strengths
  • •Auto-extracts facts and detects contradictions ("user moved SF→NYC") rather than storing raw text verbatim.
  • •Hybrid search combines vector similarity with recency and intent weighting, avoiding pure embedding noise.
  • •Versioning + multi-tenancy built-in means audit trails and scoped isolation from day one.
Weaknesses
  • •Convex + Gemini lock-in limits switching costs and offline operation; competes against Pinecone, Weaviate, Milvus.
  • •No benchmarks or production case studies shown; unclear performance vs. simple RAG stacks (Langchain + postgres + pgvector).
Target Audience

AI/LLM application developers building multi-turn agents and conversational systems

Similar To

Pinecone (vector search + metadata) · Weaviate (semantic search + versioning) · LanceDB (local vector store with fact extraction)

Post Description

I was building AI agents and kept running into the same problem – they forget everything. Every conversation starts from zero. I wanted something that could: - Auto-extract facts from conversations (not just store raw text) - Handle "user moved from SF to NYC" without keeping both as true - Search by meaning, not just keywords - Version everything (who said what, when)

Tech stack: - TypeScript + Hono (fast, edge-ready) - Convex (real-time DB + vector search) - Gemini (embeddings + extraction)

What it does: # Store memory curl -X POST /v1/content -d '{"content": "User loves hiking, lives in SF"}'

# Recall naturally curl -X POST /v1/recall -d '{"query": "outdoor hobbies"}' # Returns: "User loves hiking" with assembled context

It handles the boring stuff – chunking, embeddings, deduplication, contradiction detection, versioning – so you can focus on your actual product.

Links: - GitHub: https://github.com/akhilponnada/aethene - API Docs: OpenAPI spec in repo

This is my first time launching anything publicly. Would love feedback – what's missing? What would make you actually use this? Roast my code if you want, I can take it.

Thanks for reading.

Similar Projects