OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Agentic Workflow Patterns

Agentic Workflow Patterns is an open-source Python repository of examples and templates for building modular single-agent and collaborative multi-agent workflows. It demonstrates patterns for reflection, web access, semantic routing, parallel delegation, sharding, task decomposition and YAML-defined DAG orchestration.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agentic Workflow Patterns — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the repository as a code reference when choosing or prototyping a workflow pattern for agent collaboration, routing, parallel processing or task decomposition.

Who it is for

  • Python developers exploring agent workflow architecture.
  • Teams prototyping automation that divides work among specialized agents.
  • Contributors interested in adapting or extending reusable workflow examples.

Documented uses

  • Iteratively generate and refine content using an Actor-Critic pattern.
  • Retrieve, process and summarize web content through specialized agents.
  • Route requests by semantic intent to specialist agents.
  • Split independent subtasks or large datasets for parallel processing.
  • Represent ordered workflow tasks as a YAML-defined DAG.
Before you choose

Requirements & limits

The repository is public and identifies an MIT license. The README specifies Python 3.8 or later and documents Google Cloud and SerpAPI credentials for its setup.

  • The examples span both single-agent and collaborative multi-agent designs.
  • Some patterns depend on external services: the documented setup includes Google Cloud service-account credentials and a SerpAPI key.
  • The project provides examples and templates in a repository, not a hosted workflow service.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the Python repository and documented credentials

Prepare the repository's Python environment and credential files for experimenting with its workflow examples.

Before you start

  • Python 3.8 or later
  • pip
  • A Google Cloud project and service-account JSON key
  • A SerpAPI account and API key

Steps

  1. Clone the repository and change into its directory.

  2. Create and activate a virtual environment, then upgrade pip and install dependencies from requirements.txt.

  3. Create a credentials folder in the project root and save the Google Cloud service-account JSON key there as key.json.

  4. Create key.yml in the credentials folder and add the SerpAPI token under the serp.key field.

Expected outcome

A local Python environment with the documented dependencies and credential files in place for experimenting with the included patterns.

Guide limitations

  • This setup does not itself run a workflow.
  • The guide describes credentials for Google Cloud and SerpAPI; it does not establish requirements for every pattern.
  • The repository README says the credentials folder is included in .gitignore.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
arunpshankar/Agentic-Workflow-Patterns · Official homepage title · retained in its source language
How we review sourcesSuggest a correction