Perplexity Memory
https://www.perplexity.ai/help-center/en/articles/10968016-memory
Stores preferences and details (and optionally search history) to personalize answers, citing which memory was used; user controls in Settings → Memory. 'Brain' adds structured self-improving memory for Max subscribers and shared project Brains in Computer; Enterprise memories are org-owned and admin-managed.
Active · Verified 2026-10-23 · fresh as of 2026-10-23 · 50 cited facts, 3 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Auto-distillation across model swaps vendor fix
- Tier
- T1
- Section
- Platform-provider memory
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Free + paid vendor fix
- Funding
- $1.4B total $20.0B val Series F · 2025-09 vendor fix
- Freshness
- 2026-10-23 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
- SDK languages
- python, rest, typescript vendor fix
- Protocols
- mcp-server vendor fix
- Compliance
- fedramp, gdpr, hipaa, iso27001, pci-dss, soc2-type2 vendor fix
Memory 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
- yes — first-party Perplexity MCP server (remote at api.perplexity.ai/mcp; local perplexityai/modelcontextprotocol, npm @perplexity-ai/mcp-server) exposing search/ask/research/reason
- A2A
- not supported
- OpenTelemetry
- no — consumer product
Alternatives to Perplexity Memory → live options ranked by shared design, licence, hosting and MCP support
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.
- Vertex AI Memory Bank (now Agent Platform Memory Bank) T2
Google Cloud managed memory service, now 'Agent Platform Memory Bank' in Gemini Enterprise Agent Platform. LLM-based memory extraction/consolidation from sessions (background, multimodal, custom topics), per-identity isolation, similarity search, TTL, revisions; used from ADK via VertexAiMemoryBankService.
- 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
Public-beta memory stores for Claude Managed Agents: workspace-scoped collections of text documents mounted into the session sandbox as a directory the agent reads and writes with its file tools; every change is versioned for audit and point-in-time restore, and memories can also be managed via API/Console.
- Cloudflare Agent Memory T2
Managed persistent memory service for AI agents on Cloudflare's edge. Private beta announced 2026-04-17. Sits alongside Workers AI / Vectorize as the memory tier of the Cloudflare agent stack.
- Google Gemini Memory T1
Gemini app learns from past chats via the Personal context setting (on by default, can be disabled; temporary chats excluded). Users can import memories and full chat history from ChatGPT, Claude and other assistants (18+, personal accounts, not EEA/CH/UK).
Sources (49 cited facts, 3 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Auto-distillation across model swaps vendor
- What it does & what's distinct Stores preferences and details (and optionally search history) to personalize answers, c… vendor
- Claims / benefits 95% recall (Feb 2026 update, up from 77%) while reducing memory count by ~50%. vendor
- Modalities text vendor
- Created 2022-09 vendor
- Mindshare Perplexity blog + TC / Verge coverage of memory rollout; covered as part of broader Perp… vendor
- Funding $1.4B total $20.0B val Series F · 2025-09 vendor
- Customers / scale Pro/Enterprise subscribers — exact count undisclosed; Perplexity ~$200M ARR as of Feb 2026 vendor
- Pricing Free + paid vendor
- Compliance SOC 2 Type II; GDPR-compliant; HIPAA (Enterprise Pro/Max with BAA) vendor
- Data handling Enterprise: never trains on customer data; deleted memories retained up to 30 days for s… vendor
- Deployment Managed-only vendor
- HQ US third-party
- Founders / pedigree Perplexity AI; co-founders Aravind Srinivas (IIT Madras + UC Berkeley PhD; ex-OpenAI/Goo… third-party
- Memory volume / scale internal — undisclosed vendor
- Backend storage custom vendor
- Multi-tenancy hard-isolation vendor
- Encryption at-rest + in-transit vendor
- Embedding model locked vendor
- Tombstoning hard-delete supported vendor
- Schema evolution free-form / no schema vendor
- Contradiction handling LLM resolves and overwrites vendor
- Forgetting policy user-controlled forget vendor
- MCP support yes — first-party Perplexity MCP server (remote at api.perplexity.ai/mcp; local perplexi… vendor
- A2A support not supported vendor
- OTel no — consumer product vendor
- Webhooks / events no vendor
- Import / export no export (consumer product) vendor
- Validated verticals consumer / individual research / power users vendor
- Time to running <10min (Perplexity Pro sign-up) vendor
- Anti-fit not for enterprise programmatic memory; consumer-only vendor
- Optimised for auto-distillation across model swaps vendor
- Adjacent infrastructure self-contained Perplexity Pro vendor
- Pros Memory layered onto a search-grounded answer engine means recalled facts arrive with cit… vendor
- Cons Primarily helps repeat-search scenarios; less useful as general assistive memory than co… vendor
- Project & sources help center vendor
- cost-input-usd-per-mtok 0 vendor
- cost-output-usd-per-mtok 0 vendor
- cost-tier free vendor
- cost-pricing-model free-tier vendor
- cost-last-verified 2026-06-29 vendor
- adoption-accelerator ai-grant third-party
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product product vendor
- taxonomy-three-layer-rollup agent-infra repo
- compliance-certifications fedramp,gdpr,hipaa,iso27001,pci-dss,soc2-type2 vendor
- sdk-languages python,rest,typescript vendor
- protocol-support mcp-server vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)