OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

Dialop

DialOp is a Python research project providing game logic, text-based agent interfaces and web interfaces for collaborative decision-oriented dialogue. Its environments model conference-paper reviewer assignment, itinerary planning and group-flight coordination, with documented options for human-human play, text-based self-play and playing with GPT-3 as an assistant.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Dialop — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use DialOp when you need structured examples of dialogue-based collaboration across optimization, planning or mediation tasks, or a starting point for prototyping and evaluating collaborative agents.

Who it is for

  • Researchers studying human-AI collaboration and decision-oriented dialogue
  • Developers prototyping collaborative language agents
  • Teams creating dialogue-based agent tasks or benchmarks

Documented uses

  • Explore how dialogue can help participants assign conference-paper reviewers.
  • Prototype itinerary planning that considers travel and price.
  • Model group-flight coordination as a shared decision task.
  • Play a scenario through a text interface or a human-human web interface.
Before you choose

Requirements & limits

The repository provides installation and usage instructions and refers to a license file; the license terms are not specified here. The documented GPT-3 mode requires an API key. The Planning map features require a MapboxGL access key.

  • The project distinguishes game logic, text-based agent interfaces and web apps for human-human play.
  • The three built-in scenarios cover reviewer assignment, itinerary planning and group-flight coordination.
  • The README documents both text-based self-play and a GPT-3 assistant mode.
  • Planning's map display and related map features have an additional MapboxGL key requirement.

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 DialOp to play a game with GPT-3

Install the project, configure its API-key file and launch one of the documented GPT-3 assistant games.

Before you start

  • Python and pip
  • An API key entered in dialop/.api_key
  • A local copy of the DialOp repository

Steps

  1. Run the command below from the project directory.

    Documented command
    pip install -e .

  2. Enter the API key in dialop/.api_key.

  3. Run the command below, replacing optimization with planning or mediation as needed.

    Documented command
    python dialop/play_gpt3.py --game optimization

Expected outcome

The documented command starts the selected game with GPT-3 as an assistant.

Guide limitations

  • Planning requires a MapboxGL access key in static/client.js and static/map.js to show the map on the agent side and access other map features.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
jlin816/dialop · Official homepage title · retained in its source language
How we review sourcesSuggest a correction