Metaorcha

Developer Docs

architecture · spec · sdk

Core Architecture6 min read

SuperAgent Execution Pipeline

How one natural language goal transforms into a verified, protocol-dispatched DAG graph.

SuperAgent Execution Pipeline

#

When a user submits a goal to Metaorcha, the SuperAgent acts as the top-level executor. It does not perform domain tasks directly; instead, it manages the workflow state machine.

SuperAgent Execution Pipeline Diagram6-Phase Harness
  1. 1. PLAN
    Goal → DAG
  2. 2. ROUTE
    Vector DID Search
  3. 3. DISPATCH
    Protocol Handler
  4. 4. VERIFY
    Semantic Judge
  5. 5. NORMALIZE
    Context State
  6. 6. RENDER
    CanvasKit UI

Pipeline Phases

#
  1. Goal Decomposition (Planner): Analyzes the prompt and breaks it into discrete sub-tasks with dependency links (DAG).
  2. Agent Discovery & Routing: Queries the Registry using vector search and capability filters to match sub-tasks to registered DIDs (did:orcha:agent:*).
  3. Protocol Dispatch: Routes each step to its corresponding protocol handler (MCPHandler, A2AHandler, ComputerUseHandler, LangGraphHandler, etc.).
  4. Verification & Judging: Passes agent outputs through the ExecutionObserver for schema compliance and semantic quality check.
  5. State Normalization: Aggregates verified outputs into a structured context window.
  6. CanvasKit Rendering: Converts aggregated data into a declarative JSON layout for frontend visualization.