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

Represent accounts, transactions, variances, and reports as linked objects so close state survives across spreadsheets, dashboards, and chat threads.

Entities
Selected node
Account
Account: 4100
Account
Type
Account
Account
4100
State
Needs reconciliation
Cycle
March close
Relationships
Transaction Stripe payoutsreconciles_toAccount Account 4100
02

Connect sources

Pull data from accounting systems, payment processors, CSV imports, and close checklists through MCP tools and scheduled syncs.

Finance source inputs

Variance memory stays credible because it is tied back to ledgers, payment systems, and close artifacts.

TypeSourceAdded context
ERPGeneral ledger dataPull account state and period close context from the finance system of record.
PaymentsStripe payouts and refundsBring payout timing and refund behavior into the same variance graph.
ImportCSV reconciliationsLoad one-off analyses and exceptions without losing the source artifact behind them.
WorkflowClose checklistConnect reporting milestones and unresolved items to the same operational record.
03

Let users connect their data

Use API keys and service accounts for finance systems while keeping access scoped outside the worker runtime.

How finance data is connected

Sensitive financial access stays scoped and auditable while agents still get the context they need.

AccessSystemHow it works
API keyFinance SaaS toolsUse centrally managed credentials for accounting and payment providers.
Service accountInternal pipelinesAttach warehouse or reconciliation jobs without exposing long-lived secrets.
ManualException importsAllow operators to load one-off close evidence when automation is not the right path.
IsolationWorker boundaryThe agent reasons over reconciled state, not raw credentials or unrestricted system access.
04

Reuse context across agents

The same variance memory powers finance agents wherever teams work.

Finance agents

The same variance memory powers finance agents wherever teams work.

Variance analyst
Explains why an account moved and what still needs reconciliation before close.
Slack
Reporting assistant
Carries reconciliation context into month-end updates and leadership reporting.
Connect from Claude
Exception triage agent
Surfaces which refunds, payouts, or adjustments still need owner follow-up.
Connect from ChatGPT
Audit prep workflow
Keeps explanations attached to the originating systems and imported evidence.
Install to OpenClaw
05

Keep it fresh

Watchers keep balances, exception lists, and report status current as new payouts and adjustments arrive.

Freshness watcher

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

Month-end variance trackerEvery 6 hours
Track Account 4100 variance, refund activity, and month-end deck readiness.
Extraction schema
{ variance_amount, likely_causes[], unresolved_items[], report_status }
Schema evolution
Started with variance_amount + report_status. After repeated closes, added likely_causes and unresolved_items.

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