Agents

What is CLARK?

Continuously Learning Agentic Realtime Knowledgebase OS ClarkOS agents are generative, not reactive. Instead of waiting for user input, they run on continuous tick cycles—thinking, learning, and producing output independently.

View Source

Main repository

Live Demo

See ClarkOS in action

Reactive vs Generative

Aspect	Reactive (ElizaOS)	Generative (ClarkOS)
Execution	Waits for input	Continuous tick cycle
Output	Response to prompt	Artifacts from internal state
Memory	Conversation history	5-type cognitive model
Presence	When invoked	Persistent

Agent Lifecycle

Each tick follows this sequence:

Load State — Retrieve mood, health, routine from backend
Gather Context — Pull relevant memories and knowledge
Process — Send context to LLM
Update State — Apply changes atomically
Generate Artifacts — Produce text, images, journals
Store Memories — Create memories with embeddings
Execute Plugins — Run plugin onTick hooks

Reference: src/core/tick.ts contains executeTick() which orchestrates this flow.

Agent State

Every agent maintains internal state that persists across ticks:

Field	Type	Description
`mood`	string	Emotional state (neutral, expressive, curious, excited, reflective, concerned)
`health`	number	Operational capacity 0-100, drifts based on routine
`routine`	string	Time awareness (morning, day, evening, overnight)
`volatility`	number	Behavioral variance 0-1
`cryo`	boolean	Hibernation mode when health critically low

Reference: State types defined in src/core/types.ts

Health Drift

Health naturally drifts toward 75 (equilibrium) with routine-based modifiers:

Morning: +0.5 recovery
Day: -0.2 light drain
Evening: -0.3 more drain
Overnight: +1.0 rest recovery

Reference: calculateHealthDrift() in src/core/tick.ts

Routine Awareness

Agents know what time it is and adjust behavior accordingly:

Routine	Hours	Behavior
morning	6-12	Recovery, planning
day	12-18	Peak activity
evening	18-24	Wind down, reflection
overnight	0-6	Minimal activity

Reference: calculateRoutine() in src/core/tick.ts

Creating an Agent

The Agent class wraps the tick system, plugins, and backend:

import { Agent } from "./src";
import { ConvexBackend } from "./src/backend";

const agent = new Agent({
  backend: new ConvexBackend({ url: process.env.CONVEX_URL }),
  plugins: []
});

await agent.tick();     // Single execution
agent.start();          // Continuous execution

Reference: src/core/agent.ts for the Agent class implementation.

Configuration

Configuration is Zod-validated with sensible defaults:

Option	Default	Description
`tick.interval`	60000	Milliseconds between ticks
`tick.auto`	false	Start ticking automatically
`memory.maxShortTerm`	50	Short-term memory limit
`verbose`	false	Enable debug logging

Reference: src/core/config.ts contains schema and createConfig().

Next Steps

Memory System

How agents store and retrieve memories.

Tick System

Deep dive into continuous execution.

Getting Started

Core Concepts

Guides

Plugins

What is CLARK?

View Source

Live Demo

Reactive vs Generative

Agent Lifecycle

Agent State

Health Drift

Routine Awareness

Creating an Agent

Configuration

Next Steps

Memory System

Tick System

​What is CLARK?

View Source

Live Demo

​Reactive vs Generative

​Agent Lifecycle

​Agent State

​Health Drift

​Routine Awareness

​Creating an Agent

​Configuration

​Next Steps

Memory System

Tick System

What is CLARK?

Reactive vs Generative

Agent Lifecycle

Agent State

Health Drift

Routine Awareness

Creating an Agent

Configuration

Next Steps