{"id":"anthropic-claude-memory--platform-claude-com","name":"Anthropic Claude Memory","url":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/anthropic-claude-memory--platform-claude-com","family":"memory","section":"Platform-provider memory","sections":["Platform-provider memory"],"tier":1,"last_verified_at":"2026-10-23","lifecycle":{"status":"active","severity":0,"note":null},"taxonomy":{"storage":[{"value":"file","primary":true,"reason":null}],"retrieval":[{"value":"extraction-pull","primary":true,"reason":null},{"value":"injection","primary":false,"reason":null}],"persistence":[{"value":"long-term","primary":true,"reason":null}],"update":[{"value":"consolidation","primary":true,"reason":null},{"value":"agent-controlled","primary":false,"reason":null}],"unit":[{"value":"fact","primary":true,"reason":null},{"value":"summary","primary":false,"reason":null}],"governance":[{"value":"user-controllable","primary":true,"reason":null}],"conflict":[{"value":"manual","primary":true,"reason":null}]},"cells":{"type":{"value":"File-backed + tool-driven + Auto Dream","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"desc":{"value":"Memory tool API + consumer \"Memory\" feature + Auto Dream consolidation. Document-as-memory rather than extracted-fact-as-memory.","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"claims":{"value":"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","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"modalities":{"value":"text","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"created":{"value":"2024-09 (Enterprise/Team rollout); 2026-03-02 (all users incl. free)","citation":"https://www.reworked.co/digital-workplace/claude-ai-gains-persistent-memory-in-latest-anthropic-update/","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"third-party"},"latest-release":{"value":"not applicable — not OSS","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-12"},"license":{"value":"not applicable — not OSS","citation":null,"status":"not-applicable","tier":"T3"},"gh":{"value":"not applicable — no GitHub repo","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-12"},"mindshare":{"value":"19 HN · 3 press","citation":"https://techcrunch.com/?s=Anthropic%20Claude%20Memory","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"third-party"},"citations":{"value":"not applicable — not academic","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-12"},"funding":{"value":"latest round $65B Series H at $965B post-money (2026-05)","citation":"https://www.orrick.com/en/News/2026/05/Anthropic-Raises-65B-Series-H-at-965B-Post-Money-Valuation","status":"real-data","tier":"T2","last_verified_at":"2026-10-22","source_class":"third-party"},"customers":{"value":"501-1000 ppl Rakuten (reported 97% fewer errors, 27% lower cost, 34% lower latency)","citation":"https://www.techzine.eu/news/devops/140836/anthropic-adds-memory-to-claude-managed-agents/","status":"real-data","tier":"T2","source_class":"third-party"},"pricing":{"value":"Free + paid","citation":"https://www.anthropic.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"compliance":{"value":"SOC 2 Type I, SOC 2 Type II, ISO 27001, ISO 42001, HIPAA (Claude for Work/API with BAA)","citation":"https://trust.anthropic.com/","status":"real-data","tier":"T2","source_class":"vendor"},"data-handling":{"value":"Opt-out available (consumer Free/Pro/Max: opt-out toggle; Enterprise/API/Bedrock/Vertex: never trains on customer data; FedRAMP in progress)","citation":"https://privacy.claude.com/en/articles/10015870-what-certifications-has-anthropic-obtained","status":"real-data","tier":"T2","source_class":"vendor"},"deployment":{"value":"Managed-only","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"hq":{"value":"US","citation":"https://www.anthropic.com/company","status":"real-data","tier":"T2","source_class":"vendor"},"founders":{"value":"Anthropic; founded Jan 2021 by Dario Amodei (ex-OpenAI VP Research), Daniela Amodei (President) and fellow ex-OpenAI staff incl. Jared Kaplan, Jack Clark, Chris Olah, Tom Brown","citation":"https://en.wikipedia.org/wiki/Anthropic","status":"real-data","tier":"T2","source_class":"third-party"},"volume":{"value":"no scale claim","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"perf":{"value":"no public benchmark scores found","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"repro":{"value":"not applicable — not a research paper","citation":null,"status":"not-applicable","tier":"T3"},"code-release":{"value":"not applicable — not a research paper","citation":null,"status":"not-applicable","tier":"T3"},"api-surface":{"value":"REST (Anthropic API), SDK: Python, TS","citation":"https://docs.anthropic.com/","status":"real-data","tier":"T2","source_class":"vendor"},"latency":{"value":"searched not found","citation":"https://docs.anthropic.com/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"throughput":{"value":"searched not found","citation":"https://docs.anthropic.com/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"backend-storage":{"value":"custom (Anthropic-managed)","citation":"https://docs.anthropic.com/","status":"real-data","tier":"T2","source_class":"vendor"},"multi-tenancy":{"value":"hard-isolation (workspace)","citation":"https://www.anthropic.com/trust","status":"real-data","tier":"T2","source_class":"vendor"},"encryption":{"value":"at-rest + in-transit","citation":"https://www.anthropic.com/trust","status":"real-data","tier":"T2","source_class":"vendor"},"sso-rbac":{"value":"SSO + RBAC","citation":"https://www.anthropic.com/trust","status":"real-data","tier":"T2","source_class":"vendor"},"embedding-model":{"value":"not applicable — proprietary memory implementation","citation":null,"status":"not-applicable","tier":"T3"},"consistency":{"value":"strong","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"versioning":{"value":"snapshots","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"tombstoning":{"value":"hard-delete supported","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","source_class":"vendor"},"schema-evolution":{"value":"free-form / no schema","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"namespace":{"value":"hierarchical","citation":"https://www.anthropic.com/news/projects","status":"real-data","tier":"T2","source_class":"vendor"},"contradiction":{"value":"always overwrite (last-write-wins)","citation":"https://claudefa.st/blog/guide/mechanics/auto-dream","status":"real-data","tier":"T2","source_class":"third-party"},"forgetting":{"value":"consolidation/summarization","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","source_class":"vendor"},"mcp-support":{"value":"native (first-party) — Claude apps consume MCP","citation":"https://www.anthropic.com/news/model-context-protocol","status":"real-data","tier":"T2","source_class":"vendor"},"a2a-support":{"value":"not supported","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"otel":{"value":"no — consumer product","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"webhooks":{"value":"no","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"import-export":{"value":"Manual export via Settings (JSON archive)","citation":"https://support.anthropic.com/","status":"real-data","tier":"T2","source_class":"vendor"},"integration-count":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"orchestration":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"programmatic-control":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"vendor-benchmarks":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-12"},"pricing-specifics":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"agent-abstraction":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"memory-primitives":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"llm-lock":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"runtimes":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"session-handling":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"validated-verticals":{"value":"consumer / individual, knowledge workers (broad)","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","source_class":"vendor"},"time-to-running":{"value":"<10min (Claude.ai sign-up; memory built-in)","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","source_class":"vendor"},"anti-fit":{"value":"not for fine-grained programmatic memory control - opaque consumer feature","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","source_class":"vendor"},"optimised-for":{"value":"user-friendly persistent memory + Auto Dream consolidation","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","source_class":"vendor"},"adjacent-infrastructure":{"value":"self-contained Claude consumer product","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","source_class":"vendor"},"pros":{"value":"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.","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"cons":{"value":"Three-tier model means developers and users see different abstractions; Auto Dream consolidation is not user-controllable.","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"links":{"value":"memory tool docs Auto Dream guide memory import tool Wiegold guide","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"obs-langsmith":{"value":"no","citation":"https://docs.claude.com/en/docs/build-with-claude/memory-tool","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-opentelemetry":{"value":"depth-floor: searched, no public evidence found","citation":"https://docs.claude.com/en/docs/build-with-claude/memory-tool","status":"depth-floor-reached","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"obs-datadog":{"value":"yes","citation":"https://docs.datadoghq.com/llm_observability/instrumentation/auto_instrumentation/?tab=python","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"third-party"},"obs-helicone":{"value":"yes","citation":"https://docs.helicone.ai/integrations/anthropic/python","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"third-party"},"obs-weave":{"value":"yes","citation":"https://weave-docs.wandb.ai/guides/integrations/anthropic","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"third-party"},"obs-langfuse":{"value":"yes","citation":"https://langfuse.com/docs/integrations/anthropic","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"third-party"},"obs-arize":{"value":"yes","citation":"https://docs.arize.com/phoenix/tracing/integrations-tracing/anthropic","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"third-party"},"obs-custom":{"value":"Inherits all Anthropic API observability integrations (memory tool is a Messages API extension)","citation":"https://docs.claude.com/en/docs/build-with-claude/memory-tool","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-token-budget":{"value":"no","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-prompt-caching":{"value":"no","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-semantic-caching":{"value":"no","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-batching":{"value":"no","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-model-routing":{"value":"no","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-streaming-only":{"value":"no","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"cost-observability-cost-attribution":{"value":"no","citation":"https://www.anthropic.com/news/memory","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-langsmith-evals":{"value":"no","citation":"https://platform.claude.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-braintrust":{"value":"no","citation":"https://platform.claude.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-weights-and-biases-agent":{"value":"no","citation":"https://platform.claude.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-helicone-evals":{"value":"no","citation":"https://platform.claude.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-custom-test-harness":{"value":"no","citation":"https://platform.claude.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-human-loop":{"value":"no","citation":"https://platform.claude.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"eval-production-traffic-replay":{"value":"no","citation":"https://platform.claude.com/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"commit-trajectory":{"value":"not applicable — no GitHub repo","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"citation-trajectory":{"value":"not applicable — non-paper row","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"download-trajectory":{"value":"not applicable — not published as a package","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"cost-input-usd-per-mtok":{"value":"0","citation":"https://www.anthropic.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"cost-output-usd-per-mtok":{"value":"0","citation":"https://www.anthropic.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"cost-tier":{"value":"free","citation":"https://www.anthropic.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"cost-pricing-model":{"value":"free-tier","citation":"https://www.anthropic.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"cost-last-verified":{"value":"2026-06-29","citation":"https://www.anthropic.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"capability-composite-score":{"value":"90","citation":null,"status":"estimate","tier":"T3"},"capability-band":{"value":"frontier","citation":null,"status":"estimate","tier":"T3"},"capability-benchmark-sources":{"value":"no benchmark of its own; capability comes from the Claude model in use (see Anthropic Claude (foundation models))","citation":null,"status":"estimate","tier":"T3"},"capability-last-verified":{"value":"2026-06-29","citation":null,"status":"estimate","tier":"T3"},"use-case-tags":{"value":"long-running-session, memory-augmented-chat, analytical-summarization","citation":null,"status":"estimate","tier":"T3"},"use-case-anti-tags":{"value":"latency-sensitive, offline-capable","citation":null,"status":"estimate","tier":"T3"},"adoption-accelerator":{"value":"","citation":null,"status":"no-data","tier":"T3"},"architecture-deployment-locus":{"value":"local","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"licensing-bucket":{"value":"commercial","citation":"https://www.anthropic.com/pricing","status":"real-data","tier":"T2","source_class":"vendor"},"positioning-platform-vs-product":{"value":"both","citation":"https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool","status":"real-data","tier":"T2","source_class":"vendor"},"taxonomy-three-layer-rollup":{"value":"agent-infra","citation":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/docs/schema/section-to-three-layer-rollup.json","status":"real-data","tier":"T1","source_class":"repo"},"developer-activity-opendigger":{"value":"","citation":null,"status":"no-data","tier":"T3"},"freshness-date":{"value":"2026-10-23","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/anthropic-claude-memory--platform-claude-com","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"csa-star,hipaa,iso27001,iso42001,soc2-type2","citation":"https://trust.anthropic.com/","status":"real-data","tier":"T2","source_class":"vendor"},"sdk-languages":{"value":"csharp,go,java,php,python,rest,ruby,typescript","citation":"https://docs.claude.com/en/api/client-sdks","status":"real-data","tier":"T2","source_class":"vendor"},"protocol-support":{"value":"","citation":null,"status":"no-data","tier":"T3"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":72,"third_party_cells":11},"edges":{"outgoing":[{"source":"anthropic-claude-memory--platform-claude-com","target":"anthropic-claude-foundation-models--anthropic-com","type":"runtime-dependency","evidence":"adjacent-infrastructure cell: self-contained Claude consumer product","citation":"https://www.anthropic.com/news/memory"}],"incoming":[]},"history":[{"date":"2026-10-22","commit":"89dcc719ed","pr":195,"kind":"update","changes":[{"field":"funding","label":"Funding / ownership","from":"Anthropic total $12.4B+ raised; $40B valuation (Series E+ 2025)","to":"latest round $65B Series H at $965B post-money (2026-05)","source":"https://www.orrick.com/en/News/2026/05/Anthropic-Raises-65B-Series-H-at-965B-Post-Money-Valuation"}]}],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}