Directory AI & Machine Learning

MMW

Persistent, portable agent memory through MCP — with provenance, isolation, conflict states, and controlled deletion.

Add to shortlist

Visit MMWmmw-staging.grifun.ru

Free planFree trial

Overview

MMW is a managed memory workspace for AI agents that communicate through the Model Context Protocol.

It stores memory outside the model and agent runtime, so teams can inspect what was saved, where it came from, and how it changed. Each record can include source provenance, revision
history, confidence and explicit verified, unverified, stale or conflict states.

Workspaces are isolated by tenant and project. Agents can search, add, update, export and delete memories through MCP. The MCP Gateway also lets a project connect to an approved
downstream MCP server through a controlled tool allowlist.
MMW has passed its technical pilot gate and is now onboarding design partners. The product is pre-revenue and has not yet established large-scale production usage.

Short description

MMW gives AI agents persistent, portable memory through MCP. Every memory stays inspectable through source provenance, revision history, tenant isolation, conflict and stale states, plus
controlled export and deletion.

Sources behind this listingSee source links, recorded dates and owner corrections.

Observed facts come from public pages. Founder-edited facts are supplied by the verified owner. AI-inferred facts are model interpretations; derived facts are calculated from other data. A source link lets you check the current page. It does not guarantee the fact is still current.

Dates show when a record was saved. Some older records use the listing’s update date; they are not proof of a fresh check. Missing source records are shown explicitly.

TaglinePersistent, portable agent memory through MCP — with provenance, isolation, conflict states, and controlled deletion.: Founder-editedRecorded 6 Sept 2026Source: mmw-staging.grifun.ru
DescriptionMMW is a managed memory workspace for AI agents that communicate through the Model Context Protocol. It stores memory outside the model and agent runtime, so teams can inspe...: Founder-editedRecorded 6 Sept 2026Source: mmw-staging.grifun.ru
Free planYes: Founder-editedRecorded 6 Sept 2026Source: mmw-staging.grifun.ru
Free trialYes: Founder-editedRecorded 6 Sept 2026Source: mmw-staging.grifun.ru
SummaryMMW gives AI agents persistent, portable memory through MCP. Every memory stays inspectable through source provenance, revision history, tenant isolation, conflict and stale sta...: Founder-editedRecorded 22 Aug 2026Source link unavailable

Key Features

Persistent agent memory exposed through MCP
Source provenance and revision history for every memory
Verified, unverified, stale and conflict memory states
Tenant, project and workspace isolation
Search, add, update, export and controlled deletion
MCP Gateway for approved downstream MCP servers
Per-project tool allowlists and connection controls
Auditable memory operations and lifecycle history

Who Is It For

Best for

Teams building MCP-based AI agents that need persistent, inspectable memory, tenant isolation, provenance, and controlled lifecycle operations.

–Not for

Teams that need an established enterprise platform with contractual SLAs, a large integration catalog, or proven large-scale deployments today.

Strengths & Weaknesses

Strengths

Strong audit trailEasy data exportGood privacy practicesStrong securityGreat developer experience

Weaknesses

Limited integrationsLimited free plan

Classification

Alternatives to MMW

See all alternatives to MMW

Community

No comments yet. Be the first to share your experience.

How we sourced this: Observed fields () were crawled from https://mmw-staging.grifun.ru/ when recorded. Source links and dates are available above. AI-inferred fields () were generated by gpt-4o-mini and are always labelled, never presented as measured fact. Founder-edited fields () have been corrected by the verified owner. Last updated: 6 September 2026. Site availability checked: 6 September 2026.