mem0-python-server

mem0server

A lightweight FastAPI wrapper around mem0 providing persistent memory over a REST API, with local reranking support.

Architecture

Component	Provider	Address
LLM	Groq (llama-3.1-8b-instant)	cloud
Vector store	Chroma	192.168.0.200:8001
Embedder	Ollama (nomic-embed-text)	192.168.0.200:11434
Reranker	local REST server	192.168.0.200:5200

Setup

python -m venv mem0env
source mem0env/bin/activate
pip install fastapi uvicorn mem0 httpx

Environment variables

Variable	Required	Default	Description
GROQ_API_KEY	✅ yes	—	Groq API key
RERANKER_URL	no	http://192.168.0.200:5200/rerank	Local reranker endpoint

export GROQ_API_KEY=your_key_here
# optional override:
export RERANKER_URL=http://localhost:5200/rerank

Running

uvicorn mem0server:app --host 0.0.0.0 --port 8420

Docker

Build

docker build -t mem0server .

Run

Option A — pass the API key directly:

docker run -p 8420:8420 -e GROQ_API_KEY=your_key_here mem0server

Option B — use your .env file:

docker run -p 8420:8420 --env-file .env mem0server

Option C — override the reranker URL as well:

docker run -p 8420:8420 \
  --env-file .env \
  -e RERANKER_URL=http://192.168.0.200:5200/rerank \
  mem0server

⚠️ Never bake your .env into the image. Always pass secrets at runtime via --env-file or -e.

API

GET /health

Returns server status and configured reranker URL.

{ "status": "ok", "reranker_url": "http://192.168.0.200:5200/rerank" }

---

POST /memories

Add a memory for a user.

{ "text": "The user prefers dark mode.", "userId": "alice" }

---

POST /memories/search

Search memories with reranking. Fetches limit * 3 candidates from mem0, then reranks them locally.

{ "query": "UI preferences", "userId": "alice", "limit": 5 }

Returns results with an added rerank_score field.

POST /memories/recent

Return the most recently created memories for a user.

{ "userId": "alice", "limit": 5 }

---

DELETE /memories

Delete memories by filter.

{ "filter": { "user_id": "alice" } }

Reranker contract

The server expects a reranker at RERANKER_URL accepting:

{
  "query": "...",
  "documents": ["doc1", "doc2", "..."],
  "top_k": 5
}

And returning:

{
  "results": [
    { "text": "doc1", "score": 0.99 },
    { "text": "doc2", "score": 0.87 }
  ]
}

If the reranker is unreachable, search falls back gracefully to the raw mem0 results.