Hosted memory APIs - verified
Mem0 Platform
Mem0 Platform is listed under hosted memory APIs. Mem0's graph memory docs say the external graph store integration has been replaced by native, built-in Graph Memory on the platform, with no Neo4j, Memgraph or other graph store to deploy. No date given. Its first listed price, in its own words: Free (Hobby plan). Stated on its pages: a knowledge graph, automatic extraction, an MCP server, self-hosting and retention or deletion controls. Read from the product's own pages on October 18, 2026.
Read from docs.mem0.ai, mem0.ai, github.com. Docs - Pricing - Compare every memory product
What changed
- Native Graph MemoryMem0 Platform
Mem0's graph memory docs say the external graph store integration has been replaced by native, built-in Graph Memory on the platform, with no Neo4j, Memgraph or other graph store to deploy. No date given.
“That integration has been replaced by native, built-in Graph Memory:”
github.com “Graph Memory is built in. There is no Neo4j, Memgraph, or other graph store to deploy, no connection strings to manage, and nothing to enable. It runs natively inside the platform and is always on.”
github.com
- Launch stage, as stated
- Not stated
No launch-stage label (GA/beta) on the pricing page or the platform overview page.
How Mem0 Platform charges
Every price line Mem0 Platform states, in its own words and units, with the quote. Nothing is converted.
| Price, in the product's words | Unit | Quote and source |
|---|---|---|
| FreeinferredInferred: Plan name from the column or card the price sits in on the pricing page; the quoted text does not name the plan. | Hobby plan | “Price Free $19/month $249/month Custom” “10,000 add requests/ month” “1,000 retrieval requests/ month” “1 project” |
| $19inferredInferred: Plan name from the column or card the price sits in on the pricing page; the quoted text does not name the plan. | per month (Starter plan) | “Price Free $19/month $249/month Custom” “50,000 add requests /month” “5,000 retrieval requests / month” |
| $249inferredInferred: Plan name from the column or card the price sits in on the pricing page; the quoted text does not name the plan. | per month (Pro plan) | “Price Free $19/month $249/month Custom” “500,000 add requests /month” “50,000 retrieval requests /month” |
| CustominferredInferred: Plan name from the column or card the price sits in on the pricing page; the quoted text does not name the plan. | Enterprise plan | “Price Free $19/month $249/month Custom” |
| Usage-based pricing available | on request | “We also support usage-based pricing for teams whose traffic doesn’t map cleanly to a fixed tier.” |
| Hobby (free) or Starter ($20/month) | per month, billed through the Vercel Marketplace integration | “Select Hobby (free) or Starter ($20/month).” |
Where Mem0 Platform's own pages disagree
- docs disagreeMem0 Starter: $19 or $20 a month
Mem0's pricing page lists $19/month in the Starter column; Mem0's Vercel Marketplace integration doc says Starter is $20/month. Both are shown as stated and not reconciled.
Vercel integration doc
Hobby (free) or Starter ($20/month)
“Select Hobby (free) or Starter ($20/month).”
github.com - docs disagreeMem0 graph memory: all plans, or Pro and Enterprise
Mem0's graph memory docs say graph memory runs on all plans, automatically; the pricing page lists Graph memory (entity linking) in the Pro and Enterprise plan cards. Both are shown as stated.
Graph memory docs
Graph memory on all plans (docs)
“Graph memory: entity extraction, linking, and the retrieval boost · All plans, automatic”
github.com Pricing page
Pricing page lists Graph memory (entity linking) in the Pro and Enterprise plan cardsinferred
“Graph memory (entity linking)”
mem0.ai
Memory model
- Memory types and scopes
Scopes: user, agent, app and session
“Scope conversations by user, agent, app, and session so memories land exactly where they belong.”
github.com Scoping identifiers on Platform: user_id, agent_id, run_id, app_idinferred
Inferred: Assigned to the managed Platform by the column order of the docs' Platform vs open source table; the quoted row does not name its columns.“Scoping identifiers · user_id, agent_id, run_id, plus app_id for app/tenant separation · user_id, agent_id, run_id only, no app_id”
github.com - Storage backend
Managed vector store (run by Mem0)
“Zero infrastructure. Mem0 runs the vector store and rerankers, so there is nothing to provision, tune, or maintain.”
github.com SQL database holds facts and metadata (source of truth)
“SQL database · Facts and metadata · The source of truth for each memory”
github.com Vector database holds embeddings for semantic similarity search
“Vector database · Embeddings · Semantic similarity search”
github.com - Knowledge graph
Yes, built-in Graph Memory, always on
“Graph Memory is built in. There is no Neo4j, Memgraph, or other graph store to deploy, no connection strings to manage, and nothing to enable. It runs natively inside the platform and is always on.”
github.com Caveat: Connections are inferred from co-occurrence, not typed edges
“connections are inferred from co-occurrence rather than declared”
github.com Graph memory on all plans (docs)
“Graph memory: entity extraction, linking, and the retrieval boost · All plans, automatic”
github.com Pricing page lists Graph memory (entity linking) in the Pro and Enterprise plan cardsinferred
Inferred: The quote is the feature line itself; that it sits in the Pro and Enterprise plan cards comes from the pricing page layout.“Graph memory (entity linking)”
mem0.ai - Retrieval
Semantic, BM25 keyword and entity signals fused
“At search time, Mem0 extracts the entities from your query and matches them against the graph. Memories connected to those entities receive a ranking boost, which is combined with semantic (vector) and keyword (BM25) scores into the single score returned on each result.”
github.com - Automatic extraction
Yes, LLM fact extraction on add
“An LLM extracts preferences, decisions, plans, and other details your agent can reuse.”
github.com
MCP, SDKs and integrations
- Official MCP server
Yes, official MCP server hosted by Mem0
“Nothing runs on your machine: the server is hosted by Mem0, and your client connects to it over HTTPS.”
github.com - SDKs
Python
“pip install mem0ai”
github.com JavaScript/TypeScript (npm)
“npm install mem0ai”
github.com - Framework integrations
LangChain
“Integrate Mem0 with LangChain to build powerful agents with memory”
github.com LangGraph
“Create complex agent workflows with memory persistence using LangGraph.”
github.com LiveKit
“Integrate Mem0 with Livekit for voice agents.”
github.com
Self-hosting, license, retention and compliance
- Self-hosting
On-prem deployment listed on the pricing page
“On-prem deployment”
mem0.ai - License
- Not stated
Hosted service; the open-source SDK license is recorded on the mem0-oss entry.
- Retention and deletion
Delete single memories, lists of IDs, or by filter
“Mem0 lets you delete a specific memory, a list of IDs, or everything that matches a filter.”
github.com Expiration date hides (does not delete) a memory
“Expiration hides a memory, it does not delete it.”
github.com Batch update and batch delete: up to 1000 memories per call
“batch_update and batch_delete apply up to 1000 memories per call”
github.com - Compliance
- Not stated
Not stated on the pricing page or the docs pages reviewed (the SDK changelog mentions compliance documentation but makes no certification claim).
Vendor-stated claims
Benchmark and latency figures as Mem0 Platform states them about itself. Vendor-stated, not measured.
- Vendor-stated
Vendor-stated: 92.5 on LoCoMo, +21 points over the previous algorithm
“92.5 on LoCoMo -- +21 points over the previous algorithm”
github.com Vendor-stated: 94.4 on LongMemEval
“94.4 on LongMemEval -- +27 points, with 98.2 on assistant memory recall”
github.com Vendor note: scores reflect the managed platform
“Scores reflect Mem0's managed platform, which includes proprietary optimizations not available in the open-source SDK”
github.com
Dataset note
Two prices for the Starter tier appear in Mem0's own sources: $19/month on mem0.ai/pricing and $20/month for the Vercel Marketplace integration; both recorded with their own sources. The docs say graph memory runs on all plans while the pricing page lists it on Pro and Enterprise cards; both recorded.
FAQ
How much does Mem0 Platform cost?
In Mem0 Platform's own terms: Free (Hobby plan); $19 (per month (Starter plan)); $249 (per month (Pro plan)); Custom (Enterprise plan); Usage-based pricing available (on request); Hobby (free) or Starter ($20/month) (per month, billed through the Vercel Marketplace integration). As of October 18, 2026; prices are not converted.
Does Mem0 Platform build a knowledge graph?
Yes, built-in Graph Memory, always on, per the vendor: "Graph Memory is built in. There is no Neo4j, Memgraph, or other graph store to deploy, no connection strings to manage, and nothing to enable. It runs natively inside the platform and is always on."
Can I self-host Mem0 Platform?
Per the vendor: "On-prem deployment" License: not stated. Hosted service; the open-source SDK license is recorded on the mem0-oss entry.
What changed at Mem0 Platform (Native Graph Memory)?
Mem0's graph memory docs say the external graph store integration has been replaced by native, built-in Graph Memory on the platform, with no Neo4j, Memgraph or other graph store to deploy. No date given.
Sources
- Source: docs.mem0.ai/platform/overview
- Source: mem0.ai/pricing
- Source: github.com/mem0ai/mem0/blob/main/docs/integrations/vercel.mdx
- Source: github.com/mem0ai/mem0/blob/main/docs/platform/features/entity-scoped-memory.mdx
- Source: github.com/mem0ai/mem0/blob/main/docs/platform/platform-vs-oss.mdx
- Source: github.com/mem0ai/mem0/blob/main/docs/platform/overview.mdx
- Source: github.com/mem0ai/mem0/blob/main/docs/core-concepts/how-it-works.mdx
- Source: github.com/mem0ai/mem0/blob/main/docs/platform/features/graph-memory.mdx
- Source: github.com/mem0ai/mem0/blob/main/docs/platform/mem0-mcp.mdx
- Source: github.com/mem0ai/mem0/blob/main/README.md
- Source: github.com/mem0ai/mem0/blob/main/docs/integrations.mdx
- Source: github.com/mem0ai/mem0/blob/main/docs/core-concepts/memory-operations/delete.mdx
- Source: github.com/mem0ai/mem0/blob/main/docs/platform/features/memory-expiration.mdx
- Source: github.com/mem0ai/mem0
Last verified from each product's own docs, pricing pages, READMEs and license files; every quote was string-matched against the page that day. This is not a benchmark. Prices are shown in the product's own unit and change without notice, so check the linked source before you commit.
Newsletter
Know when a memory layer changes
One email per week. New model releases, agent tooling changes and what they mean for what you build.