Skip to main content

​
Installation

Memorose is typically run as a Rust service plus a separate dashboard UI.

​
Prerequisites

  • Rust toolchain
  • An LLM provider key for consolidation and embedding
  • Optional: jq for the command-line examples in this docs set

​
Clone The Repository

git clone https://github.com/ai-akashic/Memorose.git
cd Memorose

​
Environment Setup

Copy the example environment file and fill in your provider settings. 
cp .env.example .env
At minimum, configure: 
LLM_PROVIDER=gemini
GOOGLE_API_KEY=your_google_api_key_here
LLM_MODEL=gemini-3.1-flash-lite-preview
EMBEDDING_MODEL=gemini-embedding-2-preview
If you want to avoid the default dashboard password warning, also set: 
DASHBOARD_ADMIN_PASSWORD=change-me

​
Configuration

Start from the shipped example: 
cp config.example.toml config.toml
The current config shape is organized around:
  • [server]
  • [database]
  • [consolidation]
  • [forgetting]
  • [graph]
  • [raft]
  • [cache]
  • [multimodal]
  • [security]
  • [telemetry]
  • [development]

​
Start The Stack

Recommended local startup: 
./scripts/start_cluster.sh start --clean --build
This starts backend nodes on 3000 and related cluster ports, and the dashboard UI on 3100.

​
Manual Server Startup

If you only want the API server: 
cargo run --release -p memorose-server

​
Verify The Installation

Check the root endpoint: 
curl http://127.0.0.1:3000/
Expected response: 
Memorose is running.

​
Dashboard

  • Dashboard UI: http://127.0.0.1:3100/dashboard
  • API redirect: http://127.0.0.1:3000/dashboard
  • Default login: admin / admin
Change the password on first use, or set DASHBOARD_ADMIN_PASSWORD before startup.
Docker Deployments: If you deploy the Dashboard using your own docker-compose.yml or docker run, you must set the DASHBOARD_API_ORIGIN environment variable on the Dashboard container to point to your backend service (e.g., DASHBOARD_API_ORIGIN=http://memorose:3000). Otherwise, API requests won’t reach the backend and you will encounter connect ECONNREFUSED 127.0.0.1:3000 errors during login.