Dakera Quickstart Guide

Get Dakera running and store your first memory in under 5 minutes.

Prerequisites

• Docker (v20.10+)
• Docker Compose (v2.0+)
• curl (for testing)

Step 1: Clone and Start

git clone https://github.com/dakera-ai/dakera-deploy
cd dakera-deploy/docker
docker compose -f docker-compose.local.yml up -d

This starts Dakera in in-memory mode — no external dependencies, no config files needed.

Step 2: Verify Health

curl http://localhost:3000/health

Expected response:

{"status":"ok"}

Step 3: Store a Memory

curl -X POST http://localhost:3000/v1/memories \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "my-agent",
    "content": "The user prefers dark mode and uses VS Code."
  }'

Step 4: Recall Memories

curl -X POST http://localhost:3000/v1/memories/recall \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "my-agent",
    "query": "What IDE does the user prefer?"
  }'

Dakera returns semantically relevant memories ranked by similarity.

Step 5: Stop

docker compose -f docker-compose.local.yml down

Next Steps

Goal	Guide
Persist data across restarts	Use docker compose up -d (default profile with MinIO)
Enable authentication	See environment-variables.md
Production deployment	See production-checklist.md
High availability	See the HA section in the README
Use an SDK	Python · TypeScript · Go · Rust