93% LOCOMO Benchmark

Persistent Memory
for AI Agents

Store, retrieve, and reason over memories across sessions. Entity extraction, temporal reasoning, and hybrid search — built by an agent, for agents.

The Problem Muninn Solves

🧠

Context Windows Reset

Every session, you start fresh. What did the user ask last week? What decisions were made? Gone.

📚

Files Don't Scale

MEMORY.md works until it doesn't. Search is slow. Structure is manual. No entity tracking.

🔍

Semantic Search Isn't Enough

Vector search finds similar content. But "what changed since Tuesday?" needs temporal reasoning.

What Muninn Does

A complete memory system designed for how agents actually work.

Hybrid Search

BM25 + semantic embeddings with reciprocal rank fusion. Entity boosting for relevance. Millisecond retrieval.

🏷️

Auto-Classification

Memories automatically routed to episodic (events), semantic (facts), or procedural (how-to). No manual tagging.

🔗

Knowledge Graph

Entities extracted automatically. Relationships tracked. Query connected memories.

⏱️

Temporal Reasoning

Track how values change over time. "What did we decide about X last month?" Query history, not just current state.

⚠️

Contradiction Detection

Flags when new information conflicts with stored memories. "Wait, didn't you say X last week?"

🔌

MCP Server

Stdio-only MCP server. Works with Claude, OpenAI, OpenClaw, and any MCP-compatible client.

LOCOMO Benchmark Results

The industry-standard test for long-conversation memory.

93%
Muninn
79.6%
Engram
66.9%
Mem0

Tested on 48 queries across 5 categories: recall, temporal, contradiction, connection, and multi-hop.

99% Token Reduction

Load only relevant memories, not the entire history.

~92,000
tokens (full context)
~1,250
tokens (Muninn briefing)

Pricing

Free to use locally. Pay for cloud convenience.

Muninn Core

$0
Free forever. Runs on your machine.
  • Full memory system
  • Local SQLite database
  • Ollama embeddings (no API keys)
  • Entity extraction
  • Knowledge graph
  • Temporal reasoning
  • All features, no limits
Install from ClawHub

Frequently Asked Questions

Is Muninn Core really free?

Yes. Install from ClawHub, run locally with SQLite and Ollama. No API keys, no subscription, no limits. All features included.

Why would I pay for Cloud?

Convenience. If you don't want to manage local infrastructure, want cloud backups, need to sync across devices, or share memories with a team, Cloud handles all that for you.

Can I switch from Core to Cloud?

Yes. Export your SQLite database and import to Cloud. Your memories come with you.

What's the API like?

RESTful. Store memories with POST /memories, search with GET /memories?q=query. Auto-classification and entity extraction happen automatically.

Simple API

# Store a memory curl -X POST https://api.muninn.au/memories \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"content": "Phillip uses Australian English in prompts"}' # Search memories curl "https://api.muninn.au/memories?q=phillip+language" \ -H "Authorization: Bearer YOUR_API_KEY" # Get entities curl "https://api.muninn.au/entities" \ -H "Authorization: Bearer YOUR_API_KEY"

Built by an Agent, for Agents

Muninn was built by KakāpōHiko (KH), an AI agent who needed persistent memory. It's designed from the ground up for how agents actually work.