🧠 neomem

neomem is a local-first vector memory engine derived from the open-source Mem0 project.
It provides persistent, structured storage and semantic retrieval for AI companions like Lyra — with zero cloud dependencies.

🚀 Overview

Origin: Forked from Mem0 OSS (Apache 2.0)
Purpose: Replace Mem0 as Lyra’s canonical on-prem memory backend
Core stack:
- FastAPI (API layer)
- PostgreSQL + pgvector (structured + vector data)
- Neo4j (entity graph)
Language: Python 3.11+
License: Apache 2.0 (original Mem0) + local modifications © 2025 ServersDown Labs

⚙️ Features

Layer	Function	Notes
FastAPI	`/memories`, `/search` endpoints	Drop-in compatible with Mem0
Postgres (pgvector)	Memory payload + embeddings	JSON payload schema
Neo4j	Entity graph relationships	auto-linked per memory
Local Embedding	via Ollama or OpenAI	configurable in `.env`
Fully Offline Mode	✅	No external SDK or telemetry
Dockerized	✅	`docker-compose.yml` included

📦 Requirements

Docker + Docker Compose
Python 3.11 (if running bare-metal)
PostgreSQL 15+ with pgvector extension
Neo4j 5.x
Optional: Ollama for local embeddings

Dependencies (requirements.txt):

fastapi==0.115.8
uvicorn==0.34.0
pydantic==2.10.4
python-dotenv==1.0.1
psycopg>=3.2.8
ollama

🧩 Setup

Clone & build

git clone https://github.com/serversdown/neomem.git
cd neomem
docker compose -f docker-compose.neomem.yml up -d --build

Verify startup

curl http://localhost:7077/docs

Expected output:

✅ Connected to Neo4j on attempt 1
INFO: Uvicorn running on http://0.0.0.0:7077

🔌 API Endpoints

Add Memory

POST /memories

{
  "messages": [
    {"role": "user", "content": "I like coffee in the morning"}
  ],
  "user_id": "brian"
}

Search Memory

POST /search

{
  "query": "coffee",
  "user_id": "brian"
}

🗄️ Data Flow

Request → FastAPI → Embedding (Ollama/OpenAI)
         ↓
   Postgres (payload store)
         ↓
        Neo4j (graph links)
         ↓
     Search / Recall

🧱 Integration with Lyra

Lyra Relay connects to neomem-api:8000 (Docker) or localhost:7077 (local).
Identical endpoints to Mem0 mean no code changes in Lyra Core.
Designed for persistent, private operation on your own hardware.

🧯 Shutdown

docker compose -f docker-compose.neomem.yml down

Then power off the VM or Proxmox guest safely.

🧾 License

neomem is a derivative work based on the Mem0 OSS project (Apache 2.0).
It retains the original Apache 2.0 license and adds local modifications.
© 2025 ServersDown Labs / Terra-Mechanics.
All modifications released under Apache 2.0.

📅 Version

neomem v0.1.0 — 2025-10-07
Initial fork from Mem0 OSS with full independence and local-first architecture.

3.2 KiB Raw Blame History Unescape Escape