MnemoverseDocs

Appearance

Persistent memory for AI agents ​

Not vector search — statistical learning.

Sign up free at console.mnemoverse.com — no credit card, 1K queries/day.

3 Lines of Python ​

python
from mnemoverse import MnemoClient

client = MnemoClient(api_key="mk_...")

# Store a memory
client.write("Retry with exponential backoff fixed the timeout issue",
             concepts=["retry", "backoff", "timeout"])

# Query — Hebbian associations expand "timeout" → "backoff", "retry"
results = client.read("how to handle timeouts?")

# Report outcome — system learns what works
client.feedback(atom_ids=[r.atom_id for r in results.items], outcome=1.0)

Not a Vector Database ​

MnemoversePinecone / Weaviate / Chroma
Core modelHebbian associations + prediction-error feedback (Rescorla-Wagner-style)Vector embeddings (cosine similarity)
Learns from outcomesYes — feedback loop updates valenceNo — static retrieval
Concept associationsThree-factor Hebbian graphNone
Memory compressionHDBSCAN consolidation + Von RestorffAccumulate forever
Query expansionAutomatic via learned associationsManual or none
Starting priceFree (1K queries/day)$25-70/mo

We don't just store and retrieve. We learn which memories matter.

How It Works ​

text
1. WRITE  →  Importance gate filters noise  →  Stored with semantic embedding
2. READ   →  Hebbian expansion  →  Valence-boosted ranking  →  Results
3. FEEDBACK  →  Outcome updates valence  →  Strengthens associations
4. CONSOLIDATE  →  HDBSCAN clusters similar  →  Prototypes + singletons

Memories that lead to good outcomes rank higher in future queries. Memories that consistently fail get suppressed. The system improves with use.

Pricing ​

FreeProTeam
Price$0/mo$29/mo$149/mo
Queries/day1,00050,000500,000
Atoms (memories)10,000500,0005,000,000
Rate limit60/min600/min3,000/min
API keys1UnlimitedUnlimited
SupportCommunityEmailSlack

Built on Research ​

  • Published: SLoD framework on arXiv (Semantic Level of Detail)
  • Benchmarked: evaluated on LoCoMo (1,986 questions) and LongMemEval — see Benchmarks for the current numbers
  • Validated: experiments across game-playing agents and academic benchmarks

Common questions ​

What is persistent memory for AI agents? Persistent memory lets an AI agent store facts, preferences, and decisions once and recall them in later sessions, instead of starting cold every time. Mnemoverse is a hosted persistent-memory API: you write a memory through one key, and any connected tool — Claude, Cursor, VS Code, ChatGPT, or a Python script — can read it back later.

How do AI agents get persistent memory? Connect Mnemoverse and the agent gains six core memory tools: memory_write, memory_read, memory_feedback, and three management tools. The agent calls memory_write to save a durable fact and memory_read to recall it on a later turn or in a new session. You get an API key (mk_live_...) free at console.mnemoverse.com — no credit card, 1,000 queries/day. See Getting Started for the first call, and Make Your Agent Use Memory for getting the agent to actually call the tools.

How is persistent memory different from vector search? A vector database does static similarity retrieval: you store embeddings and get back the nearest matches, the same way every time. Mnemoverse adds a learning layer on top of retrieval — Hebbian associations expand a query to related concepts, and a prediction-error feedback signal (Rescorla-Wagner-style) updates each memory's valence so memories that led to good outcomes rank higher next time. Retrieval is the floor, not the whole system. See Not a Vector Database above for the side-by-side.

Does the memory learn and forget over time? Yes. After a recalled memory helps or misleads, the agent calls memory_feedback; that outcome updates the memory's valence, so useful memories surface faster and consistently unhelpful ones get suppressed. HDBSCAN consolidation merges similar memories into prototypes over time, so the store does not just accumulate forever.

Next Steps ​