The agent that never forgets.
And never waits to be asked.

Run finance workflows with agents that preserve account context, track exceptions, and operate safely inside your environment.

Try the Finance demo View source on GitHub

Company

Legal Engineering Support Finance Sales

Personal

Leadership Venture Capital

Public

Agent Community Market Intelligence

Cron

Daily at 7 AM — reconciles Stripe vs NetSuite

Reconcile payment sources against the ledger, explain any variances, and prep the reconciliation note.

Trace

watcher.poll(since: last_run)

→ 3 events collected

6:58NetSuiteAccount 4100 opened with a $12,480 variance

7:00Stripe3 refunds settled after the ledger cutoff

7:03Close checklistmonth-end reconciliation note due before review

netsuite.accounts.get(4100)

→ balance $187,420 · variance $12,480

stripe.refunds.list(since: Oct 20)

→ 3 refunds · posted Oct 23

recall(account: 4100, topic: variance)

→ Sep same merchant · 3-day settlement lag

upsert(Variance Oct-4100-12480)

→ linked merchant STR-44

notes.draft(month-end-4100)

→ draft ready for sign-off

Skills

Learn about Skills →

MCP

netsuitestripenotes

Network

github.com.github.com.githubusercontent.comregistry.npmjs.org.npmjs.org

Memory

Learn about Memory →

Entities touched

AccountAccount: 4100

accountclose

TransactionTransactions: Stripe payouts

paymentssource

VarianceVariance: $42k

varianceexception

ReportReport: month-end deck

reportingevidence

Relationship

Transaction Stripe payoutsreconciles_toAccount Account 4100

Outcome →

#finance-digest

The 4100 variance traces to merchant STR-44 — same 3-day settlement lag we saw in September, $12,480 net. Month-end note is drafted and ready for your sign-off.

Available in

Slack Telegram WhatsApp Discord Teams Google Chat REST API

Live workspace

Open workspace →

Read-only preview of the Finance workspace running on Lobu.

Architecture

Every agent runs in a sandboxed container with no outbound network by default — on your infrastructure, not ours.

Messaging platforms

Slack

Block Kit, interactive actions

Mini App, inline buttons

Reply buttons, list menus

Discord

Servers, DMs, markdown replies

Teams

Channels, bots, enterprise workflows

Google Chat

Cards v2, Workspace spaces

Link users across platforms with single sign-on
Approval flows, rich cards, buttons, and more

Bring your own agent

any MCP-capable agent

Lobu Memory

Lobu

Control Plane

Secrets

Single Sign-On (IdP)

Skill Registry Traces Sandboxing

Workers never see secrets
HTTP proxy with domain allowlist
MCP proxy with per-user OAuth
BYO provider keys (Anthropic etc.)

Equip your agent

Lobu Skills

OpenClaw Runtime

User A

isolated

OpenClaw Runtime

User B

isolated

OpenClaw Runtime

User C

isolated

One sandbox per user and channel
Kata Containers / Firecracker microVMs / gVisor on GCP
virtualized bash for scaling beyond 1000 users
No direct internet access (internal network)
Nix reproducible environments
OpenTelemetry for observability

Lobu in memory benchmarks

Apples-to-apples comparison on public memory datasets. The model is GLM 5.1 via z.ai.

LongMemEval (oracle-50)

Single-session knowledge retention.

System	Overall	Answer	Retrieval	Latency
Lobu	87.1%	78.0%	100.0%	237ms
Supermemory	69.1%	56.0%	96.6%	702ms
Mem0	65.7%	54.0%	85.3%	753ms

LoCoMo-50

Multi-session conversational memory.

System	Overall	Answer	Retrieval	Latency
Lobu	57.8%	38.0%	79.5%	121ms
Mem0	41.5%	28.0%	66.9%	606ms
Supermemory	23.2%	14.0%	36.5%	532ms

Read the methodology

From the blog

Latest blog posts

memoryApr 13

Filesystem vs Database for Agent Memory

Agents need a workspace to think in and a warehouse to remember in. The filesystem is for ephemeral work. The memory layer is for durable organizational knowledge.

Read post →

tutorialApr 9

Add OpenClaw to your Next.js app in 10 minutes

Embed OpenClaw agents in a Next.js project with per-user sandboxing, MCP tools, and network isolation — no Docker required.

Read post →

mcpApr 2

MCP Is Overengineered, Skills Are Too Primitive

MCP HTTP is great for external services. MCP stdio is redundant. And most skill systems are just prompt text with no reproducibility. Here's what we built instead.

Read post →