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

Agency

Agency is a Python actor-model framework for building agent-integrated systems. It models AI agents, software interfaces and human users as agents that expose callable actions, then connects them through local or AMQP-backed spaces. Its foundation includes concurrency support, callbacks, access policies and logging for custom multi-agent applications.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agency — 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 Agency when the project requires a programmable Python foundation for coordinating agents and callable software actions. Choose LocalSpace for in-application communication and AMQPSpace when agents must communicate across a network through an AMQP server.

Who it is for

  • Python developers building custom agent-based applications.
  • Teams connecting AI agents with software systems or human users.
  • Developers experimenting with local or networked multi-agent communication.

Documented uses

  • Define agents and the actions they expose.
  • Send messages that invoke actions on other agents.
  • Connect agents within one application or across a network.
  • Add permission and review requirements to actions.
  • Prototype agent applications using OpenAI or Hugging Face examples.
Before you choose

Requirements & limits

The public GitHub repository lists an MIT license. The documented installation methods are pip and Poetry. AMQPSpace requires an AMQP server such as RabbitMQ.

  • Python is the documented implementation language and installation ecosystem.
  • LocalSpace supports communication within the same application.
  • AMQPSpace uses an AMQP server for networked agent systems.
  • Multiprocessing and multithreading support addresses concurrency needs.
  • Access policies distinguish freely permitted actions from actions requiring review.

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 a local communicating-agent application

Install Agency and create a local space in which two agents can communicate.

Before you start

  • Python environment with Agency installed using pip or Poetry.

Steps

  1. Install the package with pip install agency or poetry add agency.

  2. Define agents as Agent instances with callable actions.

  3. Create a LocalSpace instance.

  4. Add the agents to the space so they can communicate within the application.

Expected outcome

A local agent system connected through the included LocalSpace implementation.

Guide limitations

  • This recipe documents local setup and connection only; it does not establish application-specific action behavior or deployment results.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
operand/agency · Official homepage title · retained in its source language
How we review sourcesSuggest a correction