COMPARE

Compare lobu

How lobu stacks up against OpenClaw, Claude Tag, Viktor, and Town, and how event-sourced org memory and connectors work under the hood.

01/MATRIX ]

At a glance

OpenClaw (personal runtime), Claude Tag (platform coworker), Viktor and Town (managed hires), and lobu. Different jobs, not worse products.

Swipe to compare →

CapabilityOpenClawClaude TagViktor / Townlobu
What it isPersonal agent runtime@Claude in SlackManaged AI coworkerMultiplayer agent backend
Open source / self-hostYesNo (cloud)No (cloud)Yes
Multi-tenant isolationSingle-tenant shared FSPer-channel @ClaudePersonal or workspacePer channel / DM sandbox
Org memoryLocal files / sessionChannel-scopedLearned user / workspaceEvent-sourced · entities
End-to-end historySession / filesChannel contextProduct memoryFull event log agents can replay
Source ACL mirrorNoPlatform-managedPer-user OAuthFail-closed (Slack · GitHub live)
Credentials to workersOften on the hostPlatform-managedCloud OAuthNever (gateway proxy)
Human approvalsDIYManagedDraft / confirm flowsTools · writes · action modes
Connectors & reachSkills + local setupAdmin-provisionedFixed OAuth catalogSDK + agents can ship connectors
Proactive workHeartbeats / cronAsync tasksRoutines · schedulesScheduled + event-driven
PlatformsMany chat apps (local)Slack (beta)Slack · email · calendar · moreSlack · TG · WA · Discord · Teams · MCP
Embed in your productNoNoNoYes · API · MCP · multi-tenant
Model choiceAny you wireClaude onlyVendor stack16 providers
02/ORG MEMORY ]

Event-sourced memory agents can trust.

Everything that happens (connector pulls, messages, agent actions, human approvals and corrections) appends to an event log. Facts project onto typed entities (companies, projects, people, incidents). Agents don’t re-derive the world from a chat window: they read the same event history and entity state end to end, then act under ACL and approval gates.

Events
  • Append-only log of what happened
  • Source + run provenance on every fact
  • Corrections supersede, never erase
  • Full trail agents can follow end to end
Entities
  • Shared current state for the org
  • Typed objects + relationships
  • Same graph across agents and channels
  • ACL-filtered on every recall
Slack #eng
Linear
GitHub
events (append-only)
Incident:INC-442
Company:Acme
Project:checkout

Event sourcing: connectors and agent actions write the log; entities are the shared picture. Slack, web, and Claude/ChatGPT via MCP all see the same history, filtered by ACL.

How entity memory works →
03/CONNECTORS ]

Not limited to a fixed catalog.

Ship built-in connectors where they exist. When a source isn’t covered, use the Connector SDK: TypeScript definitions for auth, feeds, events, and operations. Agents run in a sandbox with code and tools, so they can draft and extend connectors the same way a human engineer would, then apply them so new sources feed the same event log and entities.

01Define

Auth methods, feed kinds (poll, webhook, virtual), event shapes, and write ops in the Connector SDK.

02Ingest

Connections append events. Agents read the log and entity graph, the same end-to-end history for everyone in the org.

03Extend

If the catalog is missing a tool, an agent can write the connector in the sandbox, then you approve and ship it.

Give every teammate a colleague.

Ship it today.

Start building
Status:// provisioning…