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

Adala

An open-source Python framework for implementing autonomous agents specialized in data labeling and data processing.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Adala — 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 Adala when the task can be expressed as a defined data-labeling skill grounded in example data and handled through a configurable runtime.

Who it is for

  • AI engineers
  • Machine-learning researchers
  • Data scientists using Python notebooks and dataframes
  • Educators and students

Documented uses

  • Build autonomous data-labeling agents for classification tasks.
  • Create Python agent workflows for labeling datasets.
  • Develop specialized agents for data annotation and processing operations.
Before you choose

Requirements & limits

The repository is public and distributed under the Apache-2.0 license. The documented quickstart requires an OpenAI API key. Installation and development paths are provided for Python environments.

  • The framework lists Python 3.8 through 3.11 as supported versions.
  • A ground-truth dataset is used to define the agent’s operating environment.
  • Skills can define labels, instructions, input templates and output templates.
  • Runtimes are configured separately and can be assigned as defaults for skills.
  • The documented example uses pandas dataframes and OpenAIChatRuntime.

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 Adala and prepare its documented quickstart

Set up Adala and the prerequisites shown for a Python notebook classification example.

Before you start

  • Python 3.8, 3.9, 3.10 or 3.11
  • An OpenAI API key
  • A Python environment with pandas available for the example

Steps

  1. Install the package with pip, or install the current repository version from GitHub.

  2. For a developer installation, clone the repository, enter its directory and run the documented Poetry installation.

  3. Set the OPENAI_API_KEY environment variable.

  4. Create training and test dataframes, then define an Agent with a StaticEnvironment, ClassificationSkill and configured OpenAIChatRuntime as shown in the quickstart.

Expected outcome

A configured Adala agent is ready to be inspected in Python using the documented classification setup.

Guide limitations

  • The documented quickstart configures and prints the agent but does not document a subsequent execution or evaluation step.
  • The example uses the OpenAIChatRuntime and requires an OpenAI API key.
Documentation 1 ↗
Evidence and transparency

Sources & review

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