OpenAI ChatGPT Memory
https://openai.com/index/memory-and-new-controls-for-chatgpt/
First-party memory in ChatGPT; auto-extracts persistent facts about the user across sessions. Apr 2025 expansion to chat-history referencing.
At a glance
- Type
- User-scoped persistent facts
- Tier
- T1
- Section
- Platform-provider memory
- Created
- 2024-02-13 (limited rollout); GA broader rollout mid-2024
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Free + paid
- Funding
- OpenAI total $57B+ raised; $300B+ valuation (2025)
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
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.
- 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
Mounts memory as files on a managed filesystem; Claude reads and writes via the same bash/code-execution tools used for agentic tasks. Unit of storage is a file — inspectable, editable, exportable by developers. Full audit log per session. Memory beta launched April 23, 2026, two weeks after Managed Agents itself launched April 8.
- Cloudflare Agent Memory T2
Managed persistent memory service for AI agents on Cloudflare's edge. Beta-launched April 2026. Sits alongside Workers AI / Vectorize as the memory tier of the Cloudflare agent stack.
- Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) T1
GA at Google Cloud Next 2026 (2026-04-22). Vertex AI rebranded as Gemini Enterprise Agent Platform; Memory Bank now "Agent Platform Memory Bank" with new continuous event-streaming + automated memory generation triggered by configurable criteria (event count or idle time). Backed by Agent Runtime that supports long-running agents that maintain state for days. Note: separate "Memory Profiles" feature reported in TheNextWeb but not surfaced in official Google Cloud release notes — treated here as unconfirmed.
- Google Gemini Memory T1
Personal Context setting + Personal Intelligence packing. Memory import from ChatGPT/Claude (Mar 2026).
Related systems
References (1)
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — backend-storage cell: custom (OpenAI-managed)