100% FREE · OPEN SOURCE · RUNS ON YOUR MACHINE

Memory that AI Agents Love !

Your agent forgets everything. Memanto fixes that.

Persistent memory for Claude Code, Cursor, Codex, and 14 other agents. 100% free, open source, and runs entirely on your machine · no API keys, no vector database, no backend.

89.8%LongMemEval
<90msrecall latency
17+integrations
›_memanto · bash
$pip install memanto
Collecting memanto...
Successfully installed memanto-0.2.0
$
memanto agent create dev-agent
> Agent namespace [dev-agent] created.
[OK] Memory nodes are listening.

remember · recall · answer

Quickstart

Up and running in one command

One pip install, pick a backend, connect your agent. Copy the commands or watch the walkthrough video.

# 1. Install the CLI
$ pip install memanto

# 2. One-time setup — pick 2 for On-Prem
$ memanto
  Choose your backend
    1  Moorcheh Cloud    (instant, needs API key)
  > 2  Moorcheh On-Prem  (Docker, no API key)
  ✓ Setup complete — server on http://localhost:8080

# 3. Plug it into your agent
$ memanto connect claude-code

# 4. That's it — your agent now remembers
$ memanto remember "We deploy with Docker on port 8080"
$ memanto recall "how do we deploy?"
Runs in Docker on your machine. Embeddings and answers via local Ollama models — nothing leaves your laptop.
memanto · walkthrough
Instant IngestionConflict ResolutionMulti-AgentSemantic TypesBuilt-in RAGZero-CostFreshnessVerifiable SourcesDeterministic SearchTemporal QueriesInstant IngestionConflict ResolutionMulti-AgentSemantic TypesBuilt-in RAGZero-CostFreshnessVerifiable SourcesDeterministic SearchTemporal Queries
Info-Theoretic ScoringSub-90ms32x Compression17 IntegrationsCross-PlatformNo API KeyLocal EmbeddingsConfidence ScoringDaily SummariesAutonomous CategorizationInfo-Theoretic ScoringSub-90ms32x Compression17 IntegrationsCross-PlatformNo API KeyLocal EmbeddingsConfidence ScoringDaily SummariesAutonomous Categorization
What you get

Less context babysitting. Fewer wasted tokens.

Not features for a spec sheet, hours and tokens you stop losing every week.

context

Never re-explain your codebase

A new session starts where the last one ended - decisions, conventions, and gotchas already in mind.

token tax

0 LLM tokens per write

Others invoke an LLM on every save. Memanto's write path costs nothing - verify it yourself.

recall

Stored → searchable, instantly

No indexing queue. Memories are findable the moment they're written - in under 90 ms.

setup

One pip install. Nothing else.

No vector database, no schema, no rerankers, no backend service to keep alive.

Origin Story

Identifying the gaps in
AI agent memory

We built Moorcheh.aifirst, the only serverless vector search that delivers this level of recall efficiency at scale. While building it, we kept running into agents that forgot everything between sessions. We asked Claude what causes agent memory to fail, it pointed to passive, static context. Six gaps. We built MEMANTO around exactly those six problems, and it wouldn't be possible without Moorcheh.ai's serverless vector infrastructure underneath.

01

Irrelevant memory dumps

Memory arrives as a blob.

02

Outdated memories

Old notes weigh as much as new.

03

Unknown memory sources

Stated, inferred, or stale, unclear.

Representative model reply
“My memory exists as a static snapshot injected into context, useful, but fundamentally passive. I can't query it, update it mid-conversation, or distinguish ‘I know this’ from ‘I was told this once.’

Tap a problem to see an example

04

All memories grouped together

All memory types collapsed flat.

05

Memory contradiction

Conflicts never reconcile.

06

Long overhead ingestion

Indexing lag and server overhead.

Desiderata Coverage

Why agents love MEMANTO

Six principles. No compromises. Built from the failure modes of every system that came before.

6 design principles

D1

Relevant results only

Instead of overloading your agent with data, Memanto finds only the exact information needed for the current task.

D2

Prioritizes new info

D3

Verifiable sources

D4

Smartly categorized

D5

Resolves contradictions

D6

Instant memory ingestion

Relevant results only
25%50%75%100%D1RELEVANTD2FRESHNESSD3SOURCESD4ORGANIZEDD5NO CONFLICTSD6INGESTMemantoMem0ZepLetta
Web Interface

Interactive Dashboard

Run memanto ui and manage agents, memories, conflicts, connections, and your on-prem backend — all from a local dashboard. Try the live demo below.

127.0.0.1:8000/ui
Developer Experience

Powerful CLI Built-in

Manage agents, store memories, and run RAG directly from your terminal.

terminal

memanto v0.2.0on-prem · localhost:8080
Integrations

Works with your entire AI stack

Connect your favorite AI assistant, or build a MEMANTO-powered agent with your favorite framework.

Memanto
memory core
Antigravity
Claude CodeCLI
Cursor
CursorIDE
Windsurf
WindsurfIDE
OpenAI
Codex CLIOpenAI
Cline
ClineAgent
GithubCopilot
GitHub CopilotEditor
ModelContextProtocol
API AgentsREST·MCP
VS CodeEditor
Gemini
Gemini CLIGoogle
Prefers TypeScript
Avoids recursive bug
Uses Supabase
Tab indent, 2 spaces
Tailwind v4
Vitest over Jest
Antigravity
Claude Code
OpenAI
Codex CLI
Cursor
Cursor
Windsurf
Windsurf
Antigravity
Antigravity
Gemini
Gemini CLI
Cline
Cline
Continue
opencode
OpenCode
Goose
Goose
RooCode
Roo Code
GithubCopilot
GitHub Copilot
Augment Code
$memantoconnect
claude-code
Frameworks & Agent Platforms
Extended Memory

MemantoClaw

Persistent, long-horizon memory for NemoClaw, bringing full MEMANTO memory capabilities natively into your agentic workflows.

MemAntoClaw preview
  • Built-in MEMANTO memory agent on NemoClaw agents
  • Semantic retrieval across sessions with zero-cost ingestion
  • Agentic calls powered by Moorcheh's native LLM, no extra API keys needed
  • Open-source and self-hostable
Comparison

Memanto vs the field

Most memory layers stop at remember + recall. Memanto adds answer, LLM-grounded responses directly from your agent's memory, with no extra API keys.

FeatureMem0ZepLettaLangMemMemantoBest
RememberStore agent memories
RecallSemantic search & retrieval
AnswerMemanto onlyLLM-grounded response from memory
Instant IngestionMemories available instantly after write
Conflict ResolutionAutomated contradiction detection
Semantic Memory Types13 built-in memory categories
Multi-Agent NamespacesIsolated memory per agent
No External API KeyBuilt-in LLM proxy, no setup
YesPartialNo
Research

SOTA on Agentic Memory Benchmarks

Memanto leads across LoCoMo and LongMemEval, the two most rigorous long-context memory benchmarks for AI agents.

Explore the Research

Read about Memanto architecture, benchmark methodology, and results.

Videos

See MEMANTO in action

Walkthroughs, deep dives, and demos showing how MEMANTO gives your agents memory.

Managing multiple AI agentic workflows using Memanto as the shared memory agent

Retrieving memory for an AI agentic workflow is much more than a search

There's more to storing memories in Memanto than just typing remember

Claude admits its memory is outdated!

Memanto's first bounty PR judgement and award ceremony

Memanto's second bounty update and third bounty announcement

Pricing

Free. Actually free.

Run MEMANTO on-prem for $0— open source, no API key, no usage caps. Prefer a managed backend? Moorcheh Cloud's free tier covers ~100,000 operations, no card required.

Free forever

MEMANTO On-Prem

$0forever
Your data never leaves your machine
  • No API key, ever
  • Unlimited memories, unlimited agents
  • Runs entirely on your machine (Docker)
  • Local embeddings & LLM via Ollama — or bring OpenAI / Cohere
  • remember · recall · answer, with built-in RAG
  • Web dashboard & full CLI included
  • Works with Claude Code, Cursor, Codex + 14 more
  • MIT licensed, open source
pip install memanto
Cloud

Want a managed backend instead?

Moorcheh Cloud is free to start: 500 credits ≈ 100,000 operations, no card required. Here's what that looks like in practice.

ScenarioOps / DayDays
Small agent10 mem/day
105,000
Medium agent50 mem/day
501,000
Large agent100 queries/day
100500
Development200 ops/day
200250

Billed per operation, not per token — and you can grab a free API key in under a minute.