receptron/graphai

GraphAI is an asynchronous data flow execution engine, which allows developers to build agentic applications by describing agent workflows as declarative data flow graphs in YAML or JSON.

What it solves

GraphAI provides a way for developers to build complex agentic applications by treating agent workflows as data flow graphs. It removes the need to hard-code logic, allowing workflows to be described declaratively in YAML or JSON formats.

How it works

It operates as an asynchronous data flow execution engine. Developers define the structure of their agent workflows as graphs, where the nodes represent actions and the edges represent the flow of data between them. These declarative definitions (JSON/YAML) are then executed by the engine to coordinate the activities of various AI agents.

Who it’s for

Developers who want to build agentic applications with flexible, declarative workflow orchestration rather than imperative code.

Highlights

  • Asynchronous data flow execution engine.
  • Declarative workflow descriptions using YAML or JSON.
  • Support for agentic applications and complex agent workflows.
  • Companion CLI and GUI tools (Grapys) for development.

Related

  • Project
    microsoft/conductor

    Conductor is a Microsoft‑maintained CLI that lets you define repeatable, deterministic multi‑agent AI workflows in YAML. It supports Copilot, Claude, and other providers, offers parallel execution, sub‑workflow composition, human‑in‑the‑loop gates, a real‑time web dashboard, and a terminal‑based fleet manager. Install via a one‑line script, run workflows locally or in CI, and keep everything version‑controlled.

  • Project
    google/adk-python

    A code-first Python framework for building, evaluating, and deploying modular AI agents and complex graph-based agentic workflows.

  • Project
    langgraph4j/langgraph4j

    A Java library for building stateful, multi-agent AI applications with support for cyclical graphs, state persistence, and integrations with LangChain4j and Spring AI.

  • Project
    agentenv/agentflow

    An orchestration framework for managing multi-agent AI workflows using dependency graphs, supporting parallel execution, iterative loops, and deployment across Docker, VMs, and cloud infrastructure.

  • Project
    conductor-oss/conductor

    An open-source durable execution platform for microservices and AI agents that turns complex workflow graphs into persisted, inspectable, and recoverable executions.