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

Quantalogic

Quantalogic is a Python framework for building language-model agents that use tools for coding, search, file operations and conversational tasks. It offers ReAct, Flow and Chat modes, with modular CodeAct and Toolbox components for code-first actions and tool integrations.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Quantalogic — 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 Quantalogic when you want to assemble an agent or workflow in Python, select a mode for the task, and connect it to documented model providers and tools.

Who it is for

  • Developers building agents to write, debug or work with code.
  • Teams composing structured processes or automation workflows.
  • Builders adding tools such as search or file operations to an agent conversation.

Documented uses

  • Create an agent that reasons through a task and takes tool actions.
  • Build a tool-using chat assistant with a selected model and tools.
  • Compose structured processes with the Flow component.
  • Use executable Python as an agent’s main action language through CodeAct.
Before you choose

Requirements & limits

The repository identifies Quantalogic as open source under the Apache-2.0 license. The documented core installation uses pip and requires Python 3.10 or later.

  • Choose ReAct for open-ended tasks involving reasoning and tool actions; Flow for structured processes; or Chat for tool-enabled conversations.
  • CodeAct is a separate extension whose primary action language is executable Python.
  • The README lists OpenAI, Anthropic and DeepSeek integrations through LiteLLM.
  • Docker is optional and described for sandboxed execution; Poetry is optional for source builds.

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 the core Quantalogic package

Set up the core package and configure model-provider credentials for agent use.

Before you start

  • Python 3.10 or later
  • An API key for a supported model provider, such as OpenAI or DeepSeek

Steps

  1. Install the core package with the command below.

    Documented command
    pip install quantalogic

  2. Create a .env file containing the provider API key, using the variable name shown in the project documentation.

  3. Consult the project’s configuration documentation for advanced settings.

Expected outcome

The core package, which includes the ReAct component, is installed and provider credentials are configured.

Guide limitations

  • Docker is optional and is described for sandboxed execution.
  • The documented setup does not by itself configure additional CodeAct, Flow or Toolbox components.
Documentation 1 ↗
Source-based practical guide

Add the CodeAct extension

Install the separately packaged CodeAct extension alongside the core framework.

Before you start

  • Python 3.10 or later
  • The core Quantalogic package

Steps

  1. Install the core package and extension with the command below.

    Documented command
    pip install quantalogic quantalogic-codeact

  2. Use the documented quantalogic_codeact command for the CodeAct shell or task interface.

Expected outcome

The CodeAct extension is installed alongside the core package; its documented interface is available through the CodeAct command.

Guide limitations

  • The README lists provider credentials as a separate configuration step for model use.
  • The installation instructions do not establish that a particular task will succeed in a given environment.
Documentation 1 ↗
Evidence and transparency

Sources & review

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