Anthropic Claude Memory
https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool
Memory tool API + consumer "Memory" feature + Auto Dream consolidation. Document-as-memory rather than extracted-fact-as-memory.
At a glance
- Type
- File-backed + tool-driven + Auto Dream
- Tier
- T1
- Section
- Platform-provider memory
- Created
- 2024-09 (Enterprise/Team rollout); 2026-03-02 (all users incl. free)
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Free + paid
- Funding
- Anthropic total $12.4B+ raised; $40B valuation (Series E+ 2025)
Taxonomy
- storage
- file
- retrieval
- extraction-pull
- persistence
- long-term
- update
- consolidation
- unit
- fact
- governance
- user-controllable
- conflict
- manual
When to use
Optimised for: user-friendly persistent memory + Auto Dream consolidation
Anti-fit: not for fine-grained programmatic memory control - opaque consumer feature
Pros & cons
Pros
Three-tier model (memory tool API + consumer Memory + Auto Dream) covers developer, user, and system layers; document-as-memory unit aligns with how humans organize information.
Cons
Three-tier model means developers and users see different abstractions; Auto Dream consolidation is not user-controllable.
Claims & capabilities
Three-tier model: memory tool API + consumer Memory feature + Auto Dream consolidation; document-as-memory unit; 2024-09 Enterprise/Team rollout, 2026-03-02 expanded to all users incl. free tier; Rakuten reported 97% fewer errors / 27% lower cost / 34% lower latency; SOC 2 Type I/II + ISO 27001 + ISO 42001 + HIPAA
Technical surface
- API surface
- REST (Anthropic API), SDK: Python, TS
- Backend storage
- custom (Anthropic-managed)
- Deployment
- Managed-only
- Embedding model
- not applicable — proprietary memory implementation
- Multi-tenancy
- hard-isolation (workspace)
- MCP
- native (first-party) — Claude apps consume MCP
- A2A
- not supported
- OpenTelemetry
- no — consumer product
Compare Anthropic Claude Memory with…
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 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).
- 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.
Related systems
References (1)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: self-contained Claude consumer product