Turn data into shared, structured memory

Owletto gives all your agents the same durable graph: connectors, recall, and managed auth without leaking credentials to the runtime.

Build Memory

How it works

Turn scattered prompts, tools, and application data into a shared context layer your agents can use everywhere.

01

Model the world

Define the people, organizations, preferences, and follow-ups your agents should recognize across conversations and synced contact data.

Entities
Selected node
Person
Entity: Alex Kim
Person
Type
Person
Name
Alex Kim
Role
Vendor onboarding owner
Works at
Acme Health
Relationships
person Alex Kimworks_atorganization Acme Health
person Alex Kimpreferspreference Weekly email summaries
02

Connect sources

Proxy MCP servers and ingest contact context from messaging apps, CRM syncs, email, and custom Connector SDK integrations through one runtime.

Support source inputs

Relationship memory comes from the same channels support teams already work in every day.

TypeSourceAdded context
InboxMessage threadsCapture promises, preference changes, and ownership notes directly from conversations.
CRMAccount syncPull company context, owners, and lifecycle state from the customer system of record.
EmailFollow-up historyAttach promised summaries, deadlines, and replies to the right person record.
KnowledgeInternal toolsBring in structured account data or operational notes through MCP and custom integrations.
03

Let users connect their data

Support OAuth for inbox and calendar context, API keys for internal tools, and imports for historical contacts without exposing credentials to agents.

How customer data is connected

Support teams can authorize inboxes, CRMs, and imports without handing secrets to the runtime.

AccessSystemHow it works
OAuthInbox and calendar contextConnect communication tools so preferences and follow-ups stay in sync.
API keyInternal support systemsStore scoped credentials centrally for ticketing or account lookup tools.
ImportHistorical contactsLoad CSV or manual records to seed memory before the next live conversation.
IsolationAgent boundaryThe support agent receives context, not the raw credentials behind it.
04

Reuse context across agents

The same relationship memory powers support agents wherever teams work.

Support agents

The same relationship memory powers support agents wherever teams work.

Support responder
Drafts replies that match customer preferences and the latest promises.
Slack
Handoff assistant
Keeps owners, commitments, and next steps intact when a case moves teams.
Connect from Claude
Account context agent
Recalls who the contact is, what they own, and what was promised last.
Connect from ChatGPT
Follow-up workflow
Turns prior asks into durable next actions that future workflows can pick up.
Install to OpenClaw
05

Keep it fresh

Watchers monitor new activity and update ownership, preferences, and follow-ups as the relationship changes.

Freshness watcher

A scheduled watcher keeps this memory current as new source changes arrive.

Contact freshnessEvery 24 hours
Monitor Alex Kim's organization for role changes, new preferences, and overdue follow-ups.
Extraction schema
{ status, role_changed, new_preferences[], overdue_tasks[] }
Schema evolution
Started with name + role. After 3 runs, added preference_history and follow_up_urgency as new patterns emerged.

Beats other memory systems on public benchmarks

Apples-to-apples comparison on public memory datasets. Same answerer (glm-5.1) and same questions.

LongMemEval (oracle-50)

Single-session knowledge retention.

SystemOverallAnswerRetrievalLatency
Lobu87.1%78.0%100.0%237ms
Supermemory69.1%56.0%96.6%702ms
Mem065.7%54.0%85.3%753ms

LoCoMo-50

Multi-session conversational memory.

SystemOverallAnswerRetrievalLatency
Lobu57.8%38.0%79.5%121ms
Mem041.5%28.0%66.9%606ms
Supermemory23.2%14.0%36.5%532ms

Start building shared memory

Model the right entities, connect your sources, and keep long-term context available across every agent workflow.

Lobu on GitHub