Skip to main content

​
Agents

Agents are the core execution units in Miteos. Each agent is a specialized AI worker with access to tools, memory, and the ability to take real-world actions.

​
Agent Types

TypeSpecializationPrimary Tools
ResearcherFind and extract information from the webBrowser, search, data extraction
BuilderCreate code, files, dashboards, applicationsCode execution, file system, deploy
AnalystProcess data, generate insights and reportsCode execution, charts, statistics
TraderMarket analysis and trade executionTrading engine, broker APIs, TradingView
EmailInbox management and outreachGmail/Outlook API, drafting, scheduling
SocialContent creation and publishingPlatform APIs, stealth browser, scheduling
CommercePurchase research and executionVirtual cards, checkout automation

​
Agent Lifecycle

Created → Thinking → Acting → [Waiting for Approval] → Complete/Error
              ↑         │
              └─────────┘ (loop until task done)

​
States

  • thinking — Agent is reasoning about the next action
  • acting — Agent is executing a tool (browsing, coding, etc.)
  • paused — Human paused the agent
  • awaiting_approval — Agent needs human confirmation for a risky action
  • complete — Task finished successfully
  • error — Agent encountered an unrecoverable error
  • killed — Admin force-stopped the agent

​
Control

​
Pause & Resume

Pause an agent at any point. It freezes mid-step and resumes exactly where it left off. 
POST /agents/{agent_id}/pause
POST /agents/{agent_id}/resume

​
Guide

Inject instructions into a running agent without stopping it: 
POST /agents/{agent_id}/guide
{"instructions": "Focus on the pricing page, ignore the blog"}

​
Cancel

Stop an agent permanently: 
POST /agents/{agent_id}/cancel

​
Approval Gating

Risky actions require human approval before execution. The system classifies actions into 4 risk levels:
RiskExamplesDefault Behavior
LowRead webpage, take screenshotAuto-approve
MediumFill form, write fileDepends on autonomy dial
HighSend email, make purchase, execute tradeAlways ask
CriticalDelete data, deploy to productionAlways ask + confirm
13 action gates across 5 categories ensure agents never take dangerous actions without consent.

​
Agent-to-Agent Communication

Agents within a task can communicate via a typed message bus:
  • data_share — Share extracted data between agents
  • request — Ask another agent for help
  • response — Reply to a request
  • handoff — Transfer work to another agent
  • coordination — Sync on shared state

​
Memory

Each agent has access to three memory layers:
  1. Working — Current task context (what it’s doing now)
  2. Session — Workspace context (persists across tasks in the same workspace)
  3. Persistent — User preferences and learned patterns (permanent)

​
Desktop Agents

In the Desktop app, agents gain additional capabilities:
  • Computer Use — Control mouse, keyboard, take full-screen screenshots
  • Browser Operator — Embedded Chromium with anti-detection and human-like input
  • IDE Operator — Open VS Code, create projects, run dev servers
  • Trading Operator — Open TradingView, identify setups, execute trades