Google Gemini Memory
https://blog.google/products/gemini/temporary-chats-privacy-controls/
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).
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 71 cited facts, 10 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Personal Context + Personal Intelligence vendor fix
- Tier
- T1
- Section
- Platform-provider memory
- Created
- 2024-11-20 (initial rollout to Gemini Advanced subscribers) third-party fix
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Free; Google AI Pro $20/mo; AI Ultra $100/mo and $200/mo tiers (US, May 2026) third-party fix
- Funding
- Google/Alphabet public (GOOGL); no separate Gemini funding vendor fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial third-party 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: Google ecosystem personal context (Gmail, Drive, Calendar)
Anti-fit: not for non-Google ecosystems
Pros & cons
Pros
Tightest integration of any memory product with personal data sources (Gmail, Drive, Calendar) where users have meaningful history.
Cons
Cross-product data sharing is a trust liability; persistence model has been less clearly communicated than ChatGPT's.
Claims & capabilities
Personal Context setting + Personal Intelligence packing; 2024-11-20 rollout to Gemini Advanced subscribers; Memory import from ChatGPT/Claude in March 2026
Technical surface
- API surface
- not applicable — consumer feature
- Backend storage
- custom (Google-managed)
- Deployment
- Managed-only
- Embedding model
- not applicable — consumer feature
- Multi-tenancy
- hard-isolation
- MCP
- via official adapter — Gemini supports MCP via ADK / extensions
- A2A
- supported — Google originated A2A
- OpenTelemetry
- no — consumer product
Compare Google Gemini Memory with…
Alternatives to Google Gemini 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.
- Grok Memory (xAI) T1
Extracts and persists facts from past conversations; applies them to future responses. Per-memory deletion UI; user can also clear all. Announced by xAI's official Grok account on 2025-04-17 ('Grok now remembers your conversations').
Sources (70 cited facts, 10 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Personal Context + Personal Intelligence vendor
- What it does & what's distinct Gemini app learns from past chats via the Personal context setting (on by default, can b… vendor
- Claims / benefits Personal Context setting + Personal Intelligence packing; 2024-11-20 rollout to Gemini A… vendor
- Modalities text vendor
- Created 2024-11-20 (initial rollout to Gemini Advanced subscribers) third-party
- Mindshare 1 HN · 1 press third-party
- Funding Google/Alphabet public (GOOGL); no separate Gemini funding vendor
- Customers / scale 1000+ ppl Consumer product, Workspace enterprise customers unnamed vendor
- Pricing Free; Google AI Pro $20/mo; AI Ultra $100/mo and $200/mo tiers (US, May 2026) third-party
- Compliance SOC 2 Type II; ISO 27001; ISO 27017; ISO 27018; FedRAMP (Google Cloud); HIPAA; GDPR-comp… vendor
- Data handling Opt-out available (consumer: trains by default; Workspace/API: never trains on customer … vendor
- Deployment Managed-only vendor
- HQ US vendor
- Founders / pedigree Google DeepMind; corporate product led by Demis Hassabis (CEO Google DeepMind) vendor
- Memory volume / scale internal — undisclosed vendor
- Backend storage custom (Google-managed) vendor
- Multi-tenancy hard-isolation vendor
- Encryption at-rest + in-transit vendor
- SSO / RBAC SSO + RBAC (Workspace) vendor
- Consistency eventual vendor
- Versioning none vendor
- Tombstoning hard-delete supported vendor
- Schema evolution free-form / no schema vendor
- Namespace primitives per-user vendor
- Contradiction handling LLM resolves and overwrites vendor
- Forgetting policy user-controlled forget vendor
- MCP support via official adapter — Gemini supports MCP via ADK / extensions vendor
- A2A support supported — Google originated A2A vendor
- OTel no — consumer product vendor
- Webhooks / events no vendor
- Import / export Google Takeout export vendor
- Validated verticals consumer / individual + Google Workspace users vendor
- Time to running <10min (Google account + Gemini) vendor
- Anti-fit not for non-Google ecosystems vendor
- Optimised for Google ecosystem personal context (Gmail, Drive, Calendar) vendor
- Adjacent infrastructure self-contained Google ecosystem vendor
- Pros Tightest integration of any memory product with personal data sources (Gmail, Drive, Cal… vendor
- Cons Cross-product data sharing is a trust liability; persistence model has been less clearly… vendor
- Project & sources DataStudios writeup enterprise personalization privacy controls blog vendor
- obs-langsmith yes third-party
- obs-opentelemetry yes vendor
- obs-datadog yes third-party
- obs-helicone yes third-party
- obs-weave yes third-party
- obs-langfuse yes third-party
- obs-arize yes third-party
- obs-custom All major LLM-observability vendors instrument Gemini / Vertex AI APIs 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
- cost-input-usd-per-mtok 0 vendor
- cost-output-usd-per-mtok 0 vendor
- cost-tier free vendor
- cost-pricing-model free-tier vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial third-party
- 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)