oracle/agent-spec

Open Agent Spec (Agent Spec) is a framework-agnostic declarative language for defining agentic systems. It defines building blocks for standalone agents and structured agentic workflows as well as common ways of composing them into multi-agent systems.

What it solves

Agent Spec is a portable, platform-agnostic configuration language designed to describe AI agents and agentic systems with high fidelity. It solves the problem of framework lock-in by allowing developers to define agents and workflows in a standardized way that can be moved across different agentic frameworks.

How it works

The project provides a specification for conceptual objects and components that compose agents, including their properties and semantics. It focuses on two primary runnable components: conversational Agents (such as ReAct agents) and structured, workflow-based Flows.

To implement this, the project provides a Python SDK (PyAgentSpec) that allows users to build compliant agents and serialize/deserialize them to JSON or YAML. To actually execute these configurations, a Runtime Adapter is used to translate the Agent Spec representation into the specific requirements of a target agentic framework (e.g., LangGraph, AutoGen, or CrewAI).

Who it’s for

Developers building agentic systems who want to maintain portability across different LLM providers and agent frameworks, and those who need a standardized way to serialize agent configurations.

Highlights

  • Platform Agnostic: Decouples agent definition from the execution environment.
  • Serialization: Native support for exporting agents to JSON/YAML format.
  • Multi-Framework Support: Includes adapters for popular frameworks like LangGraph, AutoGen, and CrewAI.
  • LMM Provider Flexibility: Supports various LLM configurations including OCI Gen AI, OpenAI, and Ollama.

Related

  • Project
    openai/openai-agents-python

    A lightweight, provider-agnostic framework for building multi-agent workflows, supporting text, voice, and sandboxed execution across various LLMs.

  • Project
    agentscope-ai/agentscope

    A production-ready agent framework that provides an SDK and a FastAPI-based service to build, deploy and scale multi-agent applications with built-in RAG and tool management.

  • Project
    AgentDock/AgentDock

    A TypeScript framework for building AI agents with configurable determinism, allowing developers to balance LLM creativity with predictable, structured workflows.

  • Project
    scaleapi/scale-agentex

    A framework for building and deploying AI agents that scales from simple chatbots to fully autonomous systems, supporting both synchronous and asynchronous workflows.

  • Project
    AgentEra/Agently

    An AI application runtime framework that provides structured outputs, observable actions, and signal-driven workflows to build reliable, production-ready AI service backends.