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

Language Decision Processes (LDP)

Language Decision Processes (LDP) is an open-source Python framework for composing language agents, environments and optimizers. It models language-agent interaction as a partially observable decision process with natural-language actions and observations, and includes examples that run agents in Aviary environments.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Language Decision Processes (LDP) — 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 LDP when developing or studying language agents whose actions and observations are natural language, especially when you want agent logic and environment interaction to remain modular.

Who it is for

  • Developers prototyping language agents and connecting them to task environments.
  • Researchers comparing agent or optimizer components in language-based decision processes.
  • Python users following the documented simple-agent or GSM8K evaluation tutorials.

Documented uses

  • Build an agent that selects actions from environment observations and maintains agent state.
  • Run a language agent in an Aviary environment.
  • Evaluate a Llama agent on GSM8K using the tutorial workflow.
  • Experiment with interchangeable agents, environments and optimizers.
Before you choose

Requirements & limits

The repository is public and identifies the project as Apache-2.0 licensed. The documented setup uses Python 3.11, 3.12 or 3.13.

  • Aviary is a companion library for defining language-agent environments; tutorials that use it require additional packages.
  • The README describes agent state, action selection and environment interaction, but does not specify particular runtime integrations beyond its examples.
  • Graphviz is needed only for exporting Graphviz visualizations.

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 LDP and tutorial dependencies

Set up the documented packages for using LDP tutorials with Aviary and the neural-network module.

Before you start

  • Python 3.11, 3.12 or 3.13
  • A local checkout of the LDP repository for the editable-install command

Steps

  1. From the repository, install LDP with the command below.

    Documented command
    pip install -e .

  2. For tutorials requiring Aviary and the neural-network module, install the command below.

    Documented command
    pip install "ldp[nn]" "fhaviary[gsm8k]"

Expected outcome

LDP is installed in editable mode, with the documented additional packages available for the tutorials.

Guide limitations

  • The second installation command is specifically documented for tutorials requiring Aviary and the neural-network module.
  • Graphviz is a separate requirement only when exporting Graphviz visualizations.
Documentation 1 ↗
Evidence and transparency

Sources & review

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