Simpliflow: A Lightweight Open-Source Framework for Rapid Creation and Deployment of Generative Agentic AI Workflows

TL;DR

Simpliflow addresses the complexity and non-determinism of existing agentic AI toolkits by offering a lightweight, open-source framework that models workflows as deterministic, linear finite-state processes defined entirely in JSON. It integrates with LiteLLM to support over 100 LLM vendors, enables AI-to-Action postprocessing, and provides human-in-the-loop capabilities with comprehensive, structured JSON logging for auditing and visualization. The paper details the architecture, core features, and a suite of use cases, and contrasts simpliflow with other frameworks to highlight its emphasis on simplicity, control, and speed. This approach lowers the barrier to rapid prototyping and scalable deployment of AI agent workflows, making it suitable for production contexts where transparency and determinism are valued.

Abstract

Generative Agentic AI systems are emerging as a powerful paradigm for automating complex, multi-step tasks. However, many existing frameworks for building these systems introduce significant complexity, a steep learning curve, and substantial boilerplate code, hindering rapid prototyping and deployment. This paper introduces simpliflow, a lightweight, open-source Python framework designed to address these challenges. simpliflow enables the rapid development and orchestration of linear, deterministic agentic workflows through a declarative, JSON-based configuration. Its modular architecture decouples agent management, workflow execution, and post-processing, promoting ease of use and extensibility. By integrating with LiteLLM, it supports over 100 Large Language Models (LLMs) out-of-the-box. We present the architecture, operational flow, and core features of simpliflow, demonstrating its utility through diverse use cases ranging from software development simulation to real-time system interaction. A comparative analysis with prominent frameworks like LangChain and AutoGen highlights simpliflow's unique position as a tool optimized for simplicity, control, and speed in deterministic workflow environments.

Figures (16)

• Figure 1: High-level System Architecture of the simpliflow framework, illustrating the interaction between the client application, the LLM integration layer, the human-in-the-loop interface, and the function layer.
• Figure 2: Example workflows provided in the "Workflows" directory of the simpliflow-usage repository simpliflow_usage_github.
• Figure 3: The Interactive Workflow JSON Generator web utility provided to easily create workflow configuration files.
• Figure 4: Directory set-up required when using simpliflow.
• Figure 5: An example JSON workflow configuration (top) and the corresponding Python code in a business application to trigger its execution (bottom).