Getting Started

Up and running in
5 minutes

No Docker. No cloud account. No configuration required to start.

Go 1.23+ macOS / Linux / Windows No external deps

Install MuninnDB

Build from source (until binaries are published):

bash

git clone https://github.com/scrypster/muninndb
cd muninndb
go build -o muninndb ./cmd/muninndb
./muninndb --version

Start the server

MuninnDB starts 4 endpoints at once — binary protocol, gRPC, REST, and the web UI:

bash

./muninndb serve

# Output:
# MuninnDB v0.1.0 starting...
# MBP   listening on :8747
# gRPC  listening on :8748
# REST  listening on :8749
# Web UI listening on :8750

Open the web UI

Visit http://localhost:8750 for the visual dashboard — decay charts, relationship graphs, live activation log.

Create an API key

bash

# REST endpoint to create a key
curl -X POST http://localhost:8749/v1/keys \
  -H "Content-Type: application/json" \
  -d '{"name": "my-agent", "vault": "default"}'

# Returns:
# {"key": "mn_live_abc123...", "vault": "default"}

Store your first memory

Using the Go or Python SDK:

package main

import (
    "context"
    "fmt"
    "github.com/scrypster/muninndb/sdk/go/muninn"
)

func main() {
    ctx := context.Background()
    mem := muninn.NewMemory("mn_live_abc123", "muninn://localhost:8747")

    // Store a memory engram
    e, err := mem.Store(ctx, &muninn.StoreRequest{
        Concept:    "user prefers dark mode",
        Content:    "Always render UI in dark theme for this user",
        Tags:       []string{"preference", "ui"},
        Confidence: 0.9,
    })
    fmt.Printf("Stored engram: %s\n", e.ID)
    _ = err
}

import muninn

mem = muninn.Memory("mn_live_abc123", "muninn://localhost:8747")

# Store a memory engram
e = mem.store(
    concept="user prefers dark mode",
    content="Always render UI in dark theme for this user",
    tags=["preference", "ui"],
    confidence=0.9,
)
print(f"Stored engram: {e.id}")

Activate relevant memories

// Find the top 5 most relevant memories for a context
results, err := mem.Activate(ctx, "what does the user want?", 5)

for _, r := range results.Engrams {
    fmt.Printf("%.2f — %s\n", r.Score, r.Concept)
    fmt.Printf("  Why: %s\n", r.Why)
}

// Output:
// 0.94 — user prefers dark mode
//   Why: BM25 match (0.78) + Hebbian boost (0.16)

# Find the top 5 most relevant memories for a context
results = mem.activate("what does the user want?", limit=5)

for r in results.engrams:
    print(f"{r.score:.2f} — {r.concept}")
    print(f"  Why: {r.why}")

# Output:
# 0.94 — user prefers dark mode
#   Why: BM25 match (0.78) + Hebbian boost (0.16)

That's it

MuninnDB automatically handles decay, Hebbian learning, and association building from here. Your memories improve the more they're used.