Mistral Le Chat — Memories

https://help.mistral.ai/en/articles/396497-how-do-you-handle-my-data-when-using-the-memories-feature

Le Chat Memories — graph-based, context-aware. Stores user preferences and past decisions; memories saved explicitly (user instruction) or inferred automatically. Coupled to "Work Mode" agentic layer.

At a glance

Type
Graph-contextual + explicit + implicit
Tier
T1
Created
2025-02 (announced alongside Pro/Team tiers in Feb 2025)
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
Free tier (limited); Pro €14.99/mo; Team ~€24.99/user/mo; Enterprise custom
Funding
Mistral AI $3.05B total raised; €11.7B valuation (Series C Sept 2025)

Taxonomy

storage
graph
retrieval
graph-traversal
persistence
long-term
update
extraction
unit
fact
governance
user-controllable
conflict
llm-arbitrate

When to use

Optimised for: graph-based explicit + implicit memories

Anti-fit: not for enterprise programmatic use

Pros & cons

Pros

First major European platform with native memory; positioning emphasizes data residency and EU compliance.

Cons

Smaller ecosystem and slower feature cadence than US competitors; memory documentation is sparse.

Claims & capabilities

86% retrieval accuracy (Mistral-stated). GDPR data-handling policy. Enterprise tier for business plans.

Technical surface

API surface
not applicable — consumer feature
Backend storage
custom
Deployment
Managed-only (Le Chat) + self-hosted (open weights models) + private cloud via enterprise
Embedding model
not applicable — consumer feature
Multi-tenancy
hard-isolation
MCP
native (first-party) — Le Chat supports MCP connectors
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).

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.