AGISTRY DOCUMENTATION
  • Overview
    • Introduction
  • How Agistry works?
  • Roadmap
  • agistry hub
  • Dashboard
  • Create your first Agent
  • Manage your Agents
  • Triggers
  • Adapters & Modules
  • Workflows
  • API Keys
  • Enterprise
  • Framework
    • Core Concepts
    • Getting Started
    • Building and Deploying
  • Execution Model
    • SDK
      • Authentication
      • Adapter Calls
      • Design Flow
    • Adapters
      • Adapter Specification
      • Adapter Schema
      • Adapter Execution
  • Registry
    • Registry Design
    • Capability Matching
  • official links
    • Website
    • GitHub
  • X/Twitter
  • Telegram
Powered by GitBook
On this page
Export as PDF
  1. Execution Model
  2. Adapters

Adapter Schema

PreviousAdapter SpecificationNextAdapter Execution

Last updated 17 days ago

Each adapter registered in Agistry must include a metadata specification that defines how it is described, invoked, validated, and composed into flows. This schema acts as the contract between the registry, the runtime, the UI, and any agents/LLMs consuming the adapter.

Adapter metadata powers:

  • UI-based configuration and validation

  • LLM planning and tool descriptions

  • Runtime input enforcement

  • Flow linking / auto-mapping

  • Audit and versioning

Adapters are not just executable functions — they are structured interfaces with rich metadata that drives automation and discoverability.

Input Schema = Contract

Agistry uses to validate inputs. This ensures that:

  • All adapter calls are safe and predictable

  • The UI can auto-generate form fields

  • LLMs understand the required parameters and types

Future updates may support Zod or OpenAPI input schema inference for dev tools.

JSON Schema