{"id":"memformer","name":"Memformer","url":null,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/memformer","family":"memory-research","section":"Recent method papers — theorized, no distinct product","sections":["Recent method papers — theorized, no distinct product"],"tier":3,"last_verified_at":"2026-10-28","lifecycle":{"status":"research-code","severity":1,"note":"research code; not maintained as a product"},"taxonomy":{"storage":[{"value":"kv-cache","primary":true,"reason":null}],"retrieval":[{"value":"attention","primary":true,"reason":null},{"value":"similarity","primary":false,"reason":null}],"persistence":[{"value":"session","primary":true,"reason":null}],"update":[{"value":"consolidation","primary":true,"reason":null}],"unit":[{"value":"kv-token","primary":true,"reason":null}],"governance":[{"value":"opaque","primary":true,"reason":null}],"conflict":[{"value":"n/a","primary":true,"reason":"not applicable (architectural external KV; trained)"}]},"cells":{"type":{"value":"External KV + Memory Replay Backprop","citation":"https://github.com/qywu/memformers","status":"real-data","tier":"T1","source_class":"repo"},"desc":{"value":"External key-value stores with similarity-based cache management; trained with Memory Replay Backpropagation.","citation":"https://github.com/qywu/memformers","status":"real-data","tier":"T1","source_class":"repo"},"claims":{"value":"External dynamic memory transformer for sequence modeling; memory replay back-propagation (MRBP) for long-range BPTT. Headline: 8.1x less memory and 3.2x faster inference vs. standard Transformers with comparable performance; baseline: standard Transformers; primary dataset: not specified in abstract (long-sequence language modeling).","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","source_class":"paper"},"modalities":{"value":"text","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","source_class":"paper"},"created":{"value":"2022-12","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"paper"},"latest-release":{"value":"no-release no-release","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"paper"},"license":{"value":"MIT","citation":"https://github.com/qywu/memformers","status":"real-data","tier":"T1","source_class":"repo"},"gh":{"value":"9★ Python","citation":"https://github.com/qywu/memformers","status":"real-data","tier":"T1","last_verified_at":"2026-05-12","source_class":"repo"},"mindshare":{"value":"77 cites · 1.2/mo · 126* / 10 forks · 6 influential SS cites","citation":"https://api.semanticscholar.org/graph/v1/paper/arXiv:2010.06891","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"paper"},"citations":{"value":"77 cites 12/yr","citation":"https://www.semanticscholar.org/paper/67ee20536c30a225b86902af2f091e28e5e19b40","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"paper"},"funding":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-06"},"customers":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"pricing":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"compliance":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"data-handling":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"deployment":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"hq":{"value":"not applicable — not a company","citation":null,"status":"not-applicable","tier":"T3"},"founders":{"value":"no data — no URL in landscape HTML; searched Memformer external KV memory replay","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","source_class":"paper"},"volume":{"value":"no scale claim — research","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","source_class":"paper"},"perf":{"value":"8.1x less memory 3.2x faster inference vs Transformer","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","source_class":"paper"},"repro":{"value":"Original team only — 10 forks of https://github.com/lucidrains/memformer (mostly fork-only; no public re-implementations identified via WebSearch)","citation":"https://github.com/lucidrains/memformer","status":"real-data","tier":"T1","source_class":"repo"},"code-release":{"value":"Code public + weights closed — https://github.com/lucidrains/memformer · stale (last commit 2020-11) · 126* / 10 forks · MIT","citation":"https://github.com/lucidrains/memformer","status":"real-data","tier":"T1","source_class":"repo"},"api-surface":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"latency":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"throughput":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"backend-storage":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"multi-tenancy":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"encryption":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"sso-rbac":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"embedding-model":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"consistency":{"value":"strong","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","source_class":"paper"},"versioning":{"value":"snapshots","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","source_class":"paper"},"tombstoning":{"value":"not specified - paper does not address this dimension","citation":"https://arxiv.org/abs/2010.06891","status":"depth-floor-reached","tier":"T2","source_class":"paper"},"schema-evolution":{"value":"schema locked","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","source_class":"paper"},"namespace":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"contradiction":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"forgetting":{"value":"consolidation/summarization","citation":"https://arxiv.org/abs/2010.06891","status":"real-data","tier":"T2","source_class":"paper"},"mcp-support":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"a2a-support":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"otel":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"webhooks":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"import-export":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"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":"2026-05-06"},"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":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"time-to-running":{"value":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"anti-fit":{"value":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"optimised-for":{"value":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"adjacent-infrastructure":{"value":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"pros":{"value":"External KV stores with similarity-based cache management, trained with Memory Replay Backprop.","citation":"https://github.com/qywu/memformers","status":"real-data","tier":"T1","source_class":"repo"},"cons":{"value":"2020 paper — superseded in production by retrieval-augmented approaches.","citation":"https://github.com/qywu/memformers","status":"real-data","tier":"T1","source_class":"repo"},"links":{"value":"arxiv 2010.06891","citation":"https://github.com/qywu/memformers","status":"real-data","tier":"T1","source_class":"repo"},"obs-langsmith":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-opentelemetry":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-datadog":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-helicone":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-weave":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-langfuse":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-arize":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-custom":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-token-budget":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-prompt-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-semantic-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-batching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-model-routing":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-streaming-only":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-observability-cost-attribution":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-langsmith-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-braintrust":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-weights-and-biases-agent":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-helicone-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-custom-test-harness":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-human-loop":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-production-traffic-replay":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"commit-trajectory":{"value":"[{\"ym\":\"2022-12\",\"cum\":8},{\"ym\":\"2023-03\",\"cum\":14},{\"ym\":\"2023-06\",\"cum\":15}]","citation":"https://github.com/qywu/memformers","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"citation-trajectory":{"value":"[{\"year\":2024,\"cum\":2,\"infl\":0},{\"year\":2025,\"cum\":6,\"infl\":2}]","citation":"https://www.semanticscholar.org/paper/67ee20536c30a225b86902af2f091e28e5e19b40","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"paper"},"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":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"cost-output-usd-per-mtok":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"cost-tier":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"cost-pricing-model":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"cost-last-verified":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"capability-composite-score":{"value":"not applicable — research paper, not a runnable capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-band":{"value":"not applicable — research paper, not a runnable capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-benchmark-sources":{"value":"not applicable — research paper, not a runnable capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-last-verified":{"value":"not applicable — research paper, not a runnable capable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-tags":{"value":"not applicable — research method paper, no deployable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-anti-tags":{"value":"not applicable — research method paper, no deployable system","citation":null,"status":"not-applicable","tier":"T3"},"adoption-accelerator":{"value":"","citation":null,"status":"no-data","tier":"T3"},"architecture-deployment-locus":{"value":"","citation":null,"status":"no-data","tier":"T3"},"licensing-bucket":{"value":"open-source","citation":"https://github.com/qywu/memformers","status":"real-data","tier":"T1","source_class":"repo"},"positioning-platform-vs-product":{"value":"","citation":null,"status":"no-data","tier":"T3"},"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":"searched not found","citation":"https://oss.open-digger.cn/github/qywu/memformers/openrank.json","status":"depth-floor-reached","tier":"T2","source_class":"third-party"},"freshness-date":{"value":"2026-10-28","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/memformer","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"","citation":null,"status":"no-data","tier":"T3"},"sdk-languages":{"value":"","citation":null,"status":"no-data","tier":"T3"},"protocol-support":{"value":"","citation":null,"status":"no-data","tier":"T3"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":26,"third_party_cells":0},"edges":{"outgoing":[{"source":"memformer","target":"compressive-transformer--arxiv-1911-05507","type":"cites","evidence":"S2 isInfluential citation","citation":"https://api.semanticscholar.org/graph/v1/paper/67ee20536c30a225b86902af2f091e28e5e19b40","isInfluential":true}],"incoming":[{"source":"membart","target":"memformer","type":"cites","evidence":"S2 isInfluential citation","citation":"https://api.semanticscholar.org/graph/v1/paper/d5df3249a372fcd7994fa43fa48a94d322b43161","isInfluential":true},{"source":"memformers-gradient-memory","target":"memformer","type":"cites","evidence":"S2 isInfluential citation","citation":"https://api.semanticscholar.org/graph/v1/paper/d5df3249a372fcd7994fa43fa48a94d322b43161","isInfluential":true}]},"history":[{"date":"2026-10-22","commit":"89dcc719ed","pr":195,"kind":"lifecycle","changes":[{"field":"decay_cause","label":"Lifecycle","from":"","to":"research-complete","first":true}]}],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}