Platform-provider memory
15 systems in the platform-provider memory category of the AI Agent Infrastructure Landscape, grouped by maturity tier.
Tier 1 — battle-tested (11)
- Anthropic Claude Memory File-backed + tool-driven + Auto Dream
Memory tool API + consumer "Memory" feature + Auto Dream consolidation. Document-as-memory rather than extracted-fact-as-memory.
- Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) Long-running agent memory with continuous event-streaming consolidation
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 …
- Google Gemini Memory Personal Context + Personal Intelligence
Personal Context setting + Personal Intelligence packing. Memory import from ChatGPT/Claude (Mar 2026).
- Grok Memory (xAI) Preference-distillation + user-deletable
Extracts and persists facts from past conversations; applies them to future responses. Per-memory deletion UI; user can also clear all.
- LinkedIn Cognitive Memory Agent Episodic + semantic + procedural (shared)
Production memory infrastructure powering LinkedIn's Hiring Assistant and other GenAI apps. Three-layer (episodic/semantic/procedural) shared memory substrate across multi-agent systems; recent-context retrieval + semantic search + summa…
- Meta AI Memory Cross-platform via Accounts Center
Stores facts from one-on-one chats and shares them across Instagram, WhatsApp, Messenger, Facebook when accounts are linked via Accounts Center. The widest cross-surface memory scope of any consumer product — propagates context across en…
- Microsoft Copilot Memory Org / tenant-scoped (Exchange-backed)
Microsoft 365 Copilot memory stored in user's Exchange mailbox with compliance alignment. GA Jul 2025.
- Mistral Agents API Platform-managed stateful conversation memory
Mistral's Agents API provides persistent conversation state across turns and sessions; runtime maintains branching conversation trees. Memory is implicit in the stateful session model rather than a separate store — agents can branch, con…
- Mistral Le Chat — Memories Graph-contextual + explicit + implicit
Le Chat Memories — graph-based, context-aware. Stores user preferences and past decisions; memories saved explicitly (user instruction) or inferred automatically. Coupled to "Work Mode" agentic layer.
- OpenAI ChatGPT Memory User-scoped persistent facts
First-party memory in ChatGPT; auto-extracts persistent facts about the user across sessions. Apr 2025 expansion to chat-history referencing.
- Perplexity Memory Auto-distillation across model swaps
Auto-infers facts from conversations and surfaces them in future responses (Pro subscribers). Cross-model: memories persist when user switches underlying model mid-session. Enterprise Memory adds org-scoped retrieval.
Tier 2 — production-ready (3)
- AWS Bedrock AgentCore Memory Managed memory in Bedrock AgentCore
AWS managed memory service for agents running on Bedrock AgentCore. Native integrations with LangChain/LangGraph and Strands. Drives long-running MCP servers + agent workloads.
- Cloudflare Agent Memory Managed persistent memory service
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.
- Vertex AI Memory Bank Managed Vertex memory service
Google Cloud managed memory service (Preview). Used by ADK's VertexAIMemoryBankService for cross-session persistent memory. Intelligently stores and retrieves memories from past user interactions.
Tier 3 — emerging (1)
- Anthropic Managed Agents — Memory Filesystem-backed cross-session persistent memory
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 sessio…