Cloudflare Agent Memory
https://www.infoq.com/news/2026/04/cloudflare-agent-memory-beta/
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.
At a glance
- Type
- Managed persistent memory service
- Tier
- T2
- Section
- Platform-provider memory
- Created
- 2026-04-17 (private beta announced Cloudflare Agents Week)
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Pay-per-use
- Funding
- Cloudflare public (NET); market cap ~$45B
Taxonomy
- storage
- hybrid
- retrieval
- similarity
- persistence
- cross-session
- update
- agent-controlled
- unit
- episode
- governance
- opaque
- conflict
- none
When to use
Optimised for: edge latency + Cloudflare-native (Workers/Durable Objects)
Anti-fit: not for non-Cloudflare-edge stacks
Pros & cons
Pros
Edge-deployed agent memory — geographically distributed by default; integrates with Workers / D1 / Durable Objects.
Cons
Cloudflare-only; cold-start latency for less-frequented edges; ecosystem still maturing.
Claims & capabilities
Beta-launched April 2026 during Cloudflare Agents Week; sits alongside Workers AI / Vectorize as the memory tier of the Cloudflare agent stack; geographically-distributed by default; integrates with Workers / D1 / Durable Objects
Technical surface
- API surface
- REST, SDK: JS/TS (Cloudflare Workers)
- Backend storage
- custom (Durable Objects + Vectorize)
- Deployment
- Managed-only
- Embedding model
- multiple supported
- Multi-tenancy
- hard-isolation
- MCP
- native (first-party) — Cloudflare Agents SDK serves MCP
- A2A
- searched not found
- OpenTelemetry
- first-class — Cloudflare Workers OTel + Logpush
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.
- 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.