v0.2.0: Multi-Agent Orchestration
The UI layer for AI agent oversight.
Components for humans who can't let agents run unchecked.
Components for humans who can't let agents run unchecked.
AI agents can now send emails, execute trades, and deploy code. When actions are irreversible, oversight stops being optional.
Implement reliable human oversight today.
$npx ax-depute@latest add <component>
Oversight in action
Agent Roster
3 working1 idle
| Agent | Current Task | Tokens | Last Active | |
|---|---|---|---|---|
| Orchestrator-PrimeOrchestrator | Running lint and formatting checks on new files | |||
| Researcher-AResearcher | Validating output against business rules | |||
| Code-Writer-1Code Writer | Writing unit tests for the payment module | |||
| Code-Writer-2QA Inspector | — |
Agents act. Humans supervise.
As AI transitions from generating text to executing irreversible actions in the real world, the primary bottleneck is no longer intelligence; it's oversight. Depute provides the UI primitives required to build safe, auditable agentic systems where humans remain in the loop.
Single Agent
6
- PlanCard
- ApprovalGate
- ConfidenceMeter
- RunControls
- ToolTrace
- ArtifactCard
Multi-Agent
11
- OrchestratorView
- AgentRoster
- SwarmMonitor
- DelegationGate
- TaskQueue
- +6 more
CLI
npx
- ax-depute@latest add <component>
- Copy source into your project
- You own the code