Meta AI Memory
https://about.fb.com/news/2025/01/building-toward-a-smarter-more-personalized-assistant/
Meta AI remembers details users share in 1:1 chats (or asks it to remember) and uses them to personalise later replies; memory launched in Facebook, Messenger and WhatsApp in the US and Canada, with separate personalised responses drawing on Facebook and Instagram account info. Group chats are excluded.
Active · Verified 2026-10-23 · fresh as of 2026-10-23 · 59 cited facts, 1 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- Cross-platform via Accounts Center vendor fix
- Tier
- T1
- Section
- Platform-provider memory
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Meta AI free; Meta One Core $7.99/mo and Premium $19.99/mo add more AI generation capacity (memory not tier-gated per announcement) vendor fix
- Funding
- parent is public fix
- Freshness
- 2026-10-23 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
Memory taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- long-term
- update
- extraction
- unit
- fact
- governance
- user-controllable
- conflict
- llm-arbitrate
When to use
Optimised for: cross-platform Meta family persistence
Anti-fit: not for enterprise / programmatic; not for users who want segregated cross-app data
Pros & cons
Pros
Native delivery via WhatsApp / Instagram / Messenger reaches billions at the app level.
Cons
Non-developer surface only; no API; cross-product data flow remains a privacy concern.
Claims & capabilities
Users can delete memories at any time; launched in the US and Canada only (Jan 2025).
Technical surface
- API surface
- not applicable — consumer feature
- Backend storage
- custom (Meta-managed)
- Deployment
- Managed-only
- Embedding model
- not applicable — consumer feature
- Multi-tenancy
- hard-isolation
- MCP
- searched not found
- A2A
- not supported
- OpenTelemetry
- no — consumer product
Compare Meta AI Memory with…
Alternatives to Meta AI Memory → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other platform-provider memory in the catalog, ranked by inbound references.
- AWS Bedrock AgentCore Memory T2
AWS managed memory service for agents running on Bedrock AgentCore. Native integrations with LangChain/LangGraph and Strands. Drives long-running MCP servers + agent workloads.
- Vertex AI Memory Bank (now Agent Platform Memory Bank) T2
Google Cloud managed memory service, now 'Agent Platform Memory Bank' in Gemini Enterprise Agent Platform. LLM-based memory extraction/consolidation from sessions (background, multimodal, custom topics), per-identity isolation, similarity search, TTL, revisions; used from ADK via VertexAiMemoryBankService.
- Anthropic Claude Memory T1
Memory tool API + consumer "Memory" feature + Auto Dream consolidation. Document-as-memory rather than extracted-fact-as-memory.
- Anthropic Managed Agents — Memory T3
Public-beta memory stores for Claude Managed Agents: workspace-scoped collections of text documents mounted into the session sandbox as a directory the agent reads and writes with its file tools; every change is versioned for audit and point-in-time restore, and memories can also be managed via API/Console.
- Cloudflare Agent Memory T2
Managed persistent memory service for AI agents on Cloudflare's edge. Private beta announced 2026-04-17. Sits alongside Workers AI / Vectorize as the memory tier of the Cloudflare agent stack.
- Google Gemini Memory T1
Gemini app learns from past chats via the Personal context setting (on by default, can be disabled; temporary chats excluded). Users can import memories and full chat history from ChatGPT, Claude and other assistants (18+, personal accounts, not EEA/CH/UK).
Sources (58 cited facts, 1 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Cross-platform via Accounts Center vendor
- What it does & what's distinct Meta AI remembers details users share in 1:1 chats (or asks it to remember) and uses the… vendor
- Claims / benefits Users can delete memories at any time; launched in the US and Canada only (Jan 2025). vendor
- Modalities text vendor
- Created 2025-01-27 (memory announced for Meta AI on Facebook, Messenger and WhatsApp) vendor
- Mindshare Meta AI Connect / FB AI press cycle; substantial mainstream coverage of cross-platform m… vendor
- Customers / scale 1000+ ppl Billions of users across WhatsApp/Instagram/Messenger/Facebook, no named enter… vendor
- Pricing Meta AI free; Meta One Core $7.99/mo and Premium $19.99/mo add more AI generation capaci… vendor
- Data handling Free: trains by default; AI+: no training; Enterprise: no training + region locking + cu… third-party
- Deployment Managed-only vendor
- HQ US (Menlo Park) vendor
- Founders / pedigree Meta; corporate product led by Yann LeCun (Chief AI Scientist) vendor
- Memory volume / scale internal — undisclosed vendor
- Backend storage custom (Meta-managed) vendor
- Multi-tenancy hard-isolation vendor
- Encryption at-rest + in-transit vendor
- Tombstoning hard-delete supported vendor
- Schema evolution free-form / no schema vendor
- Contradiction handling LLM resolves and overwrites vendor
- Forgetting policy user-controlled forget vendor
- A2A support not supported vendor
- OTel no — consumer product vendor
- Webhooks / events no vendor
- Import / export no export (consumer product) vendor
- Validated verticals consumer / individual (broad - Instagram, WhatsApp, Messenger, FB) vendor
- Time to running <10min (Meta account) vendor
- Anti-fit not for enterprise / programmatic; not for users who want segregated cross-app data vendor
- Optimised for cross-platform Meta family persistence vendor
- Adjacent infrastructure self-contained Meta family vendor
- Pros Native delivery via WhatsApp / Instagram / Messenger reaches billions at the app level. vendor
- Cons Non-developer surface only; no API; cross-product data flow remains a privacy concern. vendor
- Project & sources help center vendor
- obs-langsmith no vendor
- obs-opentelemetry no vendor
- obs-datadog no vendor
- obs-helicone no vendor
- obs-weave no vendor
- obs-langfuse no vendor
- obs-arize no vendor
- obs-custom Consumer Meta AI feature — no developer observability surface vendor
- cost-token-budget no vendor
- cost-prompt-caching no vendor
- cost-semantic-caching no vendor
- cost-batching no vendor
- cost-model-routing no vendor
- cost-streaming-only no vendor
- cost-observability-cost-attribution no vendor
- eval-langsmith-evals no vendor
- eval-braintrust no vendor
- eval-weights-and-biases-agent no vendor
- eval-helicone-evals no vendor
- eval-custom-test-harness no vendor
- eval-human-loop no vendor
- eval-production-traffic-replay no vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product product vendor
- taxonomy-three-layer-rollup agent-infra repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-23
- Homepage “https://www.meta.com/help/artificial-intelligence/948583263661526/” → “https://about.fb.com/news/2025/01/building-toward-a-smarter-more-personalized-assistant/”
- 2026-10-22
- Pricing “Free (core); Meta AI+ $10/mo (extended 90-day memory vs 30-day free)” → “Meta AI free; Meta One Core $7.99/mo and Premium $19.99/mo add more AI generation capacity (memory not tier-gated per announcement)” source