Perplexity Memory
https://www.perplexity.ai/help-center/en/articles/10968016-memory
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.
At a glance
- Type
- Auto-distillation across model swaps
- Tier
- T1
- Section
- Platform-provider memory
- Created
- 2022-09
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Free + paid
- Funding
- $1.4B total $20.0B val Series F · 2025-09
Taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- long-term
- update
- extraction
- unit
- fact
- governance
- user-controllable
- conflict
- llm-arbitrate
When to use
Optimised for: auto-distillation across model swaps
Anti-fit: not for enterprise programmatic memory; consumer-only
Pros & cons
Pros
Memory layered onto a search-grounded answer engine means recalled facts arrive with citations by construction.
Cons
Primarily helps repeat-search scenarios; less useful as general assistive memory than competitors.
Claims & capabilities
95% recall (Feb 2026 update, up from 77%) while reducing memory count by ~50%.
Technical surface
- API surface
- not applicable — consumer feature
- Backend storage
- custom
- Deployment
- Managed-only
- Embedding model
- locked
- Multi-tenancy
- hard-isolation
- MCP
- searched not found
- 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).