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

Two ways to give agents memory

Per-agent files keep memory local to one sandbox. Lobu Memory gives every agent a shared, auditable graph through MCP.

Siloed

Each agent has its own filesystem

  • no cross-agent recall
  • audit is per-agent and manual
  • tied to one sandbox / session
Shared via MCP

Agents share Lobu Memory through MCP

  • one truth across agents
  • dedup via entity model
  • inspectable + correctable

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 incidents, services, deploys, and pull requests as first-class objects so on-call context survives after the thread scrolls away.

Entities
Selected node
Incident
Entity: checkout-api degradation
Incident
Type
Incident
Status
Active
Impact
EU checkout traffic degraded
Started after
Deploy 2026.04.13.2
Relationships
Incident checkout-api degradationaffects_serviceService EU checkout
Incident checkout-api degradationtriggered_by_deployDeploy Deploy 2026.04.13.2
Incident checkout-api degradationblocked_by_prPull request PR #482
02

Connect sources

Turn live operational signals into structured incident memory.

Operational events

A scheduled watcher polls the channels and tools your team already uses, then writes the relevant signals back to the right entity. The prompt is the filter — chatter that doesn't match never becomes memory.

Trace
Watcher prompt
“Track changes to active incidents, blockers, and pending PRs for Acme. Skip OOO and personal chatter.”
watcher.poll(every: 30m)
→ 5 events collected
9:02Danpicking up INC-4421, rolling back checkout-v43
9:05Priyastill blocked on checkout cluster admin creds — can someone grant?
9:11Jaycaching layer PR is ready for review, needs to land by EOD
9:18SamOOO today — family thing
9:27Ninawriting INC-4378 postmortem, sharing draft at lunch
New memory written toCompany:Acme
  • Incident INC-4421 — checkout-v43 rollback in progress (Dan)
  • Priya blocked on checkout cluster admin creds
  • Caching layer PR pending merge by EOD (Jay)
  • INC-4378 postmortem drafting (Nina)
03

Let users connect their data

Let teams bring the tools they already use, while keeping credentials outside the worker.

Connected accounts

Let teams bring the tools they already use, while keeping credentials outside the worker.

AccountBrought byAccessUsed for
GitHub / GitLabUserOAuthPRs, commits, diffs
Slack / Linear / NotionUserOAuthNotes, tickets, team context
PagerDuty / DatadogUser or adminOAuth / tokenAlerts and incident state
AWS / GCP / internal APIsOrg adminService accountInfra and deploy metadata
Incident historyOrgImport / syncMemory bootstrap
04

Reuse context across agents

The same incident memory powers operational agents wherever teams work.

Engineering agents

The same incident memory powers operational agents wherever teams work.

Incident responder
Answers what broke, what changed, and what’s blocked now.
Slack
Deploy safety agent
Checks rollback readiness and deploy risk before action.
Install to OpenClaw
Status update agent
Drafts current impact and remediation updates from live state.
Connect from ChatGPT
Postmortem assistant
Reuses the same timeline for follow-up analysis and action items.
Connect from Claude
05

Keep it fresh

Watchers pull in new alerts, deploy state, and merged fixes so the runtime sees the latest impact and rollback options.

Freshness watcher

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

Incident freshness monitorEvery 5 minutes
Track checkout-api incident state, deploy rollbacks, and the status of PR #482.
Extraction schema
{ incident_state, impacted_regions[], rollback_ready, blocking_prs[] }
Schema evolution
Started with incident_state + deploy_id. After repeated incidents, added rollback_ready and impacted_regions fields.

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