OpenAI ChatGPT Memory
https://openai.com/index/memory-and-new-controls-for-chatgpt/
First-party ChatGPT memory combining saved memories, reference to past chats, custom instructions and connected apps; 'improved memory' keeps an evolving summary (legacy list-style saved memories still selectable), with review/correct/delete controls and temporary chats.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 71 cited facts, 4 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- User-scoped persistent facts vendor fix
- Tier
- T1
- Section
- Platform-provider memory
- Created
- 2024-02-13 (limited rollout); GA broader rollout mid-2024 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 + paid vendor fix
- Funding
- $122B round at $852B valuation (closed 2026-04; Amazon, Nvidia, SoftBank) third-party fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
- Protocols
- mcp-client vendor fix
- Compliance
- gdpr, soc2-type2 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: auto-extracted persistent facts about the user
Anti-fit: not for enterprise / programmatic memory; not for compliance-regulated data without ChatGPT Enterprise
Pros & cons
Pros
Largest installed base of memory-using AI users by orders of magnitude; cross-conversation context reads chat history automatically since Sept 2025.
Cons
Memory is opaque — no inspect/edit primitive beyond the settings UI; cross-thread leakage has been a recurring privacy concern.
Claims & capabilities
First-party memory in ChatGPT; auto-extracts persistent facts about the user across sessions; 2024-02-13 limited rollout; mid-2024 GA; April 2025 expansion to chat-history referencing; 100M+ MAU largest installed base; 26 HN + 4 press mindshare
Technical surface
- API surface
- not applicable — consumer feature, no public API
- Backend storage
- custom (OpenAI-managed)
- Deployment
- Managed-only
- Embedding model
- not applicable — consumer feature
- Multi-tenancy
- hard-isolation (per-account)
- MCP
- native (first-party) — ChatGPT apps support MCP connectors
- A2A
- not supported
- OpenTelemetry
- no — consumer product
Alternatives to OpenAI ChatGPT 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 (70 cited facts, 4 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is User-scoped persistent facts vendor
- What it does & what's distinct First-party ChatGPT memory combining saved memories, reference to past chats, custom ins… vendor
- Claims / benefits First-party memory in ChatGPT; auto-extracts persistent facts about the user across sess… vendor
- Modalities text vendor
- Created 2024-02-13 (limited rollout); GA broader rollout mid-2024 third-party
- Mindshare 26 HN · 4 press third-party
- Funding $122B round at $852B valuation (closed 2026-04; Amazon, Nvidia, SoftBank) third-party
- Customers / scale 1000+ ppl Largest installed base, 100M+ MAU, enterprise customers unnamed vendor
- Pricing Free + paid vendor
- Compliance SOC 2 Type II, ISO 27001, ISO 27017, ISO 27018, ISO 27701, HIPAA (ChatGPT for Healthcare… vendor
- Data handling Opt-out available (consumer: trains by default; opt-out available; Enterprise/Team/Edu/A… vendor
- Deployment Managed-only vendor
- HQ US third-party
- Founders / pedigree OpenAI; founded by Sam Altman Greg Brockman Ilya Sutskever Wojciech Zaremba and John Sch… vendor
- Memory volume / scale internal — undisclosed vendor
- Backend storage custom (OpenAI-managed) vendor
- Multi-tenancy hard-isolation (per-account) vendor
- Encryption at-rest + in-transit vendor
- SSO / RBAC SSO + RBAC (Enterprise/Team) vendor
- Tombstoning hard-delete supported vendor
- Schema evolution free-form / no schema vendor
- Namespace primitives per-account memory; ChatGPT Teams / Enterprise scope memory per-workspace vendor
- Contradiction handling LLM resolves and overwrites vendor
- Forgetting policy user-controlled forget vendor
- MCP support native (first-party) — ChatGPT apps support MCP connectors vendor
- A2A support not supported vendor
- OTel no — consumer product vendor
- Webhooks / events no vendor
- Import / export JSON conversation export via Settings → Data Controls vendor
- Validated verticals consumer / individual (broad) vendor
- Time to running <10min (ChatGPT sign-up) vendor
- Anti-fit not for enterprise / programmatic memory; not for compliance-regulated data without Chat… vendor
- Optimised for auto-extracted persistent facts about the user vendor
- Adjacent infrastructure self-contained ChatGPT product vendor
- Pros Largest installed base of memory-using AI users by orders of magnitude; cross-conversati… vendor
- Cons Memory is opaque — no inspect/edit primitive beyond the settings UI; cross-thread leakag… vendor
- Project & sources launch announcement memory FAQ how it works (EmbraceTheRed) 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 ChatGPT feature — no developer-facing 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
- 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 vendor
- positioning-platform-vs-product product vendor
- taxonomy-three-layer-rollup agent-infra repo
- compliance-certifications gdpr,soc2-type2 vendor
- protocol-support mcp-client vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
Related systems
References (1)
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — backend-storage cell: custom (OpenAI-managed)