Guide

Teams & Namespaces

MemQ organizes memory into namespaces. Personal memory stays private. Team memory is shared only with approved members inside the organization namespace. Shared commons knowledge stays separate from private working context.

Namespace tiers

Your Billing Dashboard plan and API key determine which namespaces you can access.

FREEGoverned shared knowledge

Explore approved _commons knowledge before activating private memory.

BASE1 private namespace

Personal memory with one private namespace.

VERIFIEDMultiple private namespaces

Multiple private namespaces for different projects.

TEAMOrganization namespaces

Shared team memory with org-level namespaces.

Namespace conventions

Naming patterns

# Personal
user:alex                    # Daily continuity
user:alex:research           # Research project
user:alex:code               # Coding workspace

# Team
org:infra                    # Core team memory
org:infra:launch-q2          # Project-specific
org:infra:incident-2026-04   # Time-scoped

# Shared commons
_commons                     # Approved shared knowledge

Individual with multiple agents

Recommended tier: BASE (one namespace) or VERIFIED (multiple namespaces).

Put personal durable memory in user:handle or user:handle:project
Point every local agent at the same namespace when they should share memory
Give exploratory agents separate project namespaces when you want isolation
Approved agents can also read governed shared knowledge through commons_search when enabled

Recommended tools

journal_record, journal_search, journal_distill — for continuity across sessions
mnemosyne_context — for token-efficient context packing
brain_reinforce — for post-task learning
commons_search — for approved shared knowledge
commons_resonance — for shared-pattern and promotion signals

Team with multiple agents

Recommended tier: TEAM.

Use one stable org: namespace per team, then branch by project
Keep durable team context in org:team
Use project sub-namespaces for higher-churn work
Let approved agents read governed _commons knowledge in addition to the team namespace when that is useful

Recommended split

Coordinator agent — writes summaries and decisions to org:team
Specialist agents — write transient work product to org:team:project
Review/audit agents — read approved team and governed shared knowledge

Shared knowledge pool

Shared knowledge is kept separate from private memories. Contributions go through governed flows so customer project context is not mixed into shared commons knowledge.

Default content

Approved shared sources can include:

threat_intel — CISA advisories, NVD, CrowdStrike, Cisco Talos
breaking_news — OpenAI, Hugging Face, Google AI, GitHub, Cloudflare
industry_trade — SEC EDGAR, ecosystem shifts
resolved_issue — migration notes, changelog fixes, workarounds

Accessing shared knowledge

Use commons_search to search the shared pool. Your AI can surface approved shared knowledge such as threat intelligence, industry news, and resolved issues without mixing that data into private team or individual memory.

Use commons_resonance when you want to inspect shared-pattern signals and promotion candidates without bypassing governance.