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.
Collecting memanto... Successfully installed memanto-0.2.0
> Agent namespace [dev-agent] created. [OK] Memory nodes are listening.
remember · recall · answer
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?"
Less context babysitting. Fewer wasted tokens.
Not features for a spec sheet, hours and tokens you stop losing every week.
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.
Irrelevant memory dumps
Memory arrives as a blob.
Outdated memories
Old notes weigh as much as new.
Unknown memory sources
Stated, inferred, or stale, unclear.
“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
All memories grouped together
All memory types collapsed flat.
Memory contradiction
Conflicts never reconcile.
Long overhead ingestion
Indexing lag and server overhead.
Why agents love MEMANTO
Six principles. No compromises. Built from the failure modes of every system that came before.
6 design principles
Relevant results only
Instead of overloading your agent with data, Memanto finds only the exact information needed for the current task.
Prioritizes new info
Verifiable sources
Smartly categorized
Resolves contradictions
Instant memory ingestion
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.
Powerful CLI Built-in
Manage agents, store memories, and run RAG directly from your terminal.
Works with your entire AI stack
Connect your favorite AI assistant, or build a MEMANTO-powered agent with your favorite framework.
$memantoconnectclaude-codeMemantoClaw
Persistent, long-horizon memory for NemoClaw, bringing full MEMANTO memory capabilities natively into your agentic workflows.
- 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
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.
| Feature | Mem0 | Zep | Letta | LangMem | MemantoBest |
|---|---|---|---|---|---|
| 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 |
SOTA on Agentic Memory Benchmarks
Memanto leads across LoCoMo and LongMemEval, the two most rigorous long-context memory benchmarks for AI agents.
Read about Memanto architecture, benchmark methodology, and results.
See MEMANTO in action
Walkthroughs, deep dives, and demos showing how MEMANTO gives your agents memory.
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.
MEMANTO On-Prem
- 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
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.
Billed per operation, not per token — and you can grab a free API key in under a minute.