Skip to main content

​
MEMANTO - Universal Memory Layer for Agentic AI

MEMANTO is a production-ready memory system for AI agents that gives them persistent, semantic long-term memory across conversations, sessions, and workflows.

​
What Problem Does It Solve?

LLMs inherently lack persistent memory, they forget conversations between sessions. Agents need a way to:
  • Remember user preferences across sessions
  • Track decisions and commitments made during conversations
  • Store facts and context for faster, smarter responses
  • Manage long-running workflows with consistent state
  • Learn from interactions over time
MEMANTO solves this with a semantic memory system built for AI agents.

​
Key Advantages

​
Zero-Cost Ingestion Latency

Unlike traditional vector databases that index after writes, MEMANTO uses no-indexing semantic search. Memories are available for retrieval immediately no waiting.

​
State-of-the-Art Accuracy

Evaluated on LongMemEval and LoCoMo benchmarks:
  • 89.8% accuracy on LongMemEval
  • 87.1% accuracy on LoCoMo
Store memories with semantic meaning (facts, preferences, decisions, events, etc.) and retrieve them intelligently by relevance, not just keywords.

​
Built on Moorcheh

MEMANTO uses Moorcheh.ai, the world’s only no-indexing semantic database:
  • Instant write-to-search (vs. minutes with traditional DBs)
  • Exact search results (vs. approximate ANN)
  • Deterministic output (vs. probabilistic)
  • 80% cost savings vs. traditional vector DBs

​
How It Works

​
1. Agent Activates Session

memanto agent activate my-customer-bot

​
2. Store Memories

memanto remember "User prefers email over phone" --type preference

​
3. Recall When Needed

memanto recall "How should we contact the user?"

​
4. Generate Grounded Answers

memanto answer "Based on stored preferences, what's the user's contact method?"

​
Quick Start

​
1. Install

pip install memanto

​
2. Configure

memanto  # Prompts for your Moorcheh API key

​
3. Create Agent

memanto agent create customer-support
memanto agent activate customer-support

​
4. Store & Recall

# Store memory
memanto remember "Alice prefers concise answers" --type preference

# Recall memory
memanto recall "What communication style does Alice prefer?"

​
5. Get AI Answers

memanto answer "How should we communicate with Alice?"

​
What You Can Build

Use CaseExampleBenefit
Customer SupportAgent remembers past issues, preferences, ticketsFaster resolution, better context
AI AssistantsAssistant recalls your style, preferences, commitmentsMore personalized interactions
Agent WorkflowsMulti-step processes maintain state across sessionsReliable long-running automation
Research ToolsTrack hypotheses, findings, decisions over timeBetter scientific documentation
Project ManagementDecisions and context persist across team discussionsClearer history, faster onboarding

​
Memory Types

MEMANTO supports rich semantic memory types:
  • fact: Objective information (“User is in PST timezone”)
  • preference: User or system preferences (“Prefers dark mode”)
  • decision: Decisions made (“Chose PostgreSQL for database”)
  • goal: Objectives to achieve (“Get 100K users by Q4”)
  • commitment: Promises made (“Will deliver report by Friday”)
  • event: What happened (“Meeting with CEO at 2pm”)
  • instruction: Rules to follow (“Always verify before sending”)
  • relationship: Connections between entities (“Alice reports to Bob”)
  • context: Contextual information (“We’re in budget review season”)
  • learning: Lessons learned (“Users need simpler onboarding”)
  • observation: What was noticed (“Traffic spikes on weekends”)
  • error: Mistakes to avoid (“Don’t use deprecated API”)
  • artifact: Important documents or code (“Q3 budget spreadsheet”)

​
Architecture Overview

​
Deployment Options

  • Docker: Fastest setup, reproducible environments
  • Python: Development and customization
  • Cloud: AWS ECS, Google Cloud Run, Azure Container Instances
  • Local: Single machine testing and prototyping

​
Next Steps

Choose your path based on your use case:

​
Need Help?