Self-Hosting Quickstart - supermemory | Memory API for the AI era

Install

curl
npx
bunx

curl -fsSL https://supermemory.ai/install | bash

npx supermemory local

bunx supermemory local

The installer detects your OS and architecture, downloads the right binary, verifies it, and (when run interactively) prompts you for an LLM API key. Supported platforms: macOS (Apple Silicon & Intel), Linux (x64 & arm64).

Run

supermemory-server

First boot sets everything up — the embedded Supermemory graph engine, local embeddings, and your credentials:

  ┌──────────────────────────────────────────────────┐
  │  url       http://localhost:6767                 │
  │  database  ./.supermemory                        │
  │  api key   sm_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx     │
  │  org id    xxxxxxxxxxxxxxxxxxxxxx                │
  └──────────────────────────────────────────────────┘

Save that API key — it’s your bearer token for every request.

In production, Supermemory runs proprietary models tuned for long-horizon data understanding. Self-hosted, you bring any model: if no provider key is set, first boot launches an interactive setup wizard — pick a provider (OpenAI, Anthropic, Gemini, Groq, or any OpenAI-compatible endpoint like Ollama), paste your key, and it’s saved encrypted for every future launch. After the LLM key, you can optionally pick an embedding model (press Enter to keep local Xenova/bge-base-en-v1.5). See all providers, embeddings, and fully-offline local models.

Docker / non-interactive: set an LLM key via env and, if you don’t want local embeddings, set SUPERMEMORY_EMBEDDING_PROVIDER / MODEL / DIMENSIONS. There is no wizard without a TTY.

Add your first memory

TypeScript
Python
curl

import Supermemory from "supermemory"

const client = new Supermemory({
  apiKey: "sm_...",
  baseURL: "http://localhost:6767",
})

await client.memories.add({
  content: "I'm Dhravya. I love building dev tools and I'm allergic to peanuts.",
  containerTag: "user_dhravya",
})

from supermemory import Supermemory

client = Supermemory(
    api_key="sm_...",
    base_url="http://localhost:6767",
)

client.memories.add(
    content="I'm Dhravya. I love building dev tools and I'm allergic to peanuts.",
    container_tag="user_dhravya",
)

curl http://localhost:6767/v3/documents \
  -H "Authorization: Bearer sm_..." \
  -H "Content-Type: application/json" \
  -d '{
    "content": "I am Dhravya. I love building dev tools and I am allergic to peanuts.",
    "containerTag": "user_dhravya"
  }'

Search it

TypeScript
Python
curl

const results = await client.search.memories({
  q: "what food should I avoid?",
  containerTag: "user_dhravya",
})

results = client.search.memories(
    q="what food should I avoid?",
    container_tag="user_dhravya",
)

curl http://localhost:6767/v3/search \
  -H "Authorization: Bearer sm_..." \
  -H "Content-Type: application/json" \
  -d '{
    "q": "what food should I avoid?",
    "containerTag": "user_dhravya"
  }'

That’s it. Everything in the Memory API — documents, memories, user profiles, spaces, filtering — works identically against your local server.

Where things live

By default, all state lives in a single directory you can back up or move:

Path	Contents
`./.supermemory/` (or `$SUPERMEMORY_DATA_DIR`)	The Supermemory graph engine’s data, auth secret, embedding model cache
`~/.supermemory/env`	API keys saved by the installer, loaded on every launch

Next steps

Configuration

LLM providers, local models, performance tuning

Embeddings

Local default, OpenAI / Gemini / Ollama, multilingual

Memory API

The full API — it all works against your local server

​Install

​Run

​Add your first memory

​Search it

​Where things live

​Next steps

Configuration

Embeddings

Memory API

Install

Run

Add your first memory

Search it

Where things live

Next steps