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

Autono

An open-source Python framework for building autonomous ReAct-based agents with dynamic action selection, MCP support and multi-agent collaboration.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Autono — 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 Autono when an agent must handle multi-step work, adapt its next action during execution or collaborate with other agents. It is also relevant for research prototypes examining tool failures, retries and dynamic decision-making.

Who it is for

  • Developers building programmable autonomous agents
  • Researchers studying adaptive agent execution
  • Teams prototyping multi-agent task-solving systems

Documented uses

  • Create agents that choose subsequent actions from prior execution trajectories
  • Define reusable functions as agent abilities
  • Coordinate multiple agents with shared and updated memory
  • Extend an agent's action space through MCP-supported tools or services
  • Compare adaptive execution with fixed planner workflows
Before you choose

Requirements & limits

The repository is public and specifies the GPL-3.0 license. The documented installation paths are PyPI and GitHub.

  • The framework is Python-based and uses a documented OpenAI API key in its quick start.
  • Its central design is trajectory-based dynamic action selection rather than only fixed LLM-generated workflows.
  • MCP support is stated, but detailed configuration and end-to-end usage instructions are limited in the supplied documentation.
  • The README reports experiments involving one-step, multi-step and failure-prone multi-step tasks.
  • The GitHub installation path is described as providing unreleased features.

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

Install Autono and begin defining an agent

Set up the documented Python package and begin declaring agent abilities.

Before you start

  • Python environment
  • An OpenAI API key stored as OPENAI_API_KEY
  • Access to PyPI or the GitHub repository

Steps

  1. Install Autono with pip from PyPI, or install the GitHub version for unreleased features.

  2. Set OPENAI_API_KEY in a .env file.

  3. Import Agent, Personality, get_openai_model, ability and agentic from autono.

  4. Declare functions as basic abilities using the documented ability mechanism.

Expected outcome

A Python project is prepared to start building an Autono agent with declared abilities.

Guide limitations

  • MCP support is confirmed, but its configuration and end-to-end usage are not documented in the supplied material.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AutonoCreate agents that choose subsequent actions from prior execution trajectoriesCLI, Self-hostedThe repository is public and specifies the GPL-3.0 license. The documented installation paths are PyPI and GitHub.
AgeniteDefine typed tools with JSON Schema validation and error handling.CLI
VeldraCreate an agent with a policy, tools, skills, knowledge base and reasoning method.Self-hostedThe documented deployment is self-hosted and uses a sign-in gate after a first-run administrator account is created.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
vortezwohl/Autono · Official homepage title · retained in its source language
How we review sourcesSuggest a correction