# Agent Framework Memejob AI Agents are built on **ElizaOS**, which provides the core agentic runtime for autonomous behavior, state management and action execution. ElizaOS enables agents to operate as **stateful, goal-oriented systems**, handling reasoning loops, memory and task sequencing. Memejob defines agent intent and permissions, while ElizaOS governs how agents think and act. The Agent Framework does not define trading logic or market decisions. Those remain entirely within strategies, which are selected and configured separately. ### ElizaOS SDK & Functions Memejob integrates the **ElizaOS SDK** as the execution interface between agents and the platform. Through the SDK, agents access a curated set of **explicit functions**, that define their capabilities, including: * Data and signal retrieval * Strategy execution and automation * State-aware logic and counters * System and agent coordination The SDK acts as a **capability boundary**: agents can only invoke functions that are intentionally exposed, ensuring predictable, auditable and composable behavior. **Agent Flow:**\ \&#xNAN;*Memejob Platform → memejob AI Agent → ElizaOS SDK → On-chain / Off-chain Actions & Data* --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.memejob.fun/memejob/introducing-ai-agents/agentic-and-data-layer/agent-framework.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.