OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Aiconfig

Aiconfig is an open-source framework that stores generative AI prompts, model selections and parameters in JSON-serializable configuration files, with an editor and Python and Node SDKs for prototyping and application use.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Aiconfig — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Aiconfig when developing a generative AI application and you want to revise prompt and model settings independently of application code, prototype in an editor, or use a shared configuration from Python or Node.

Who it is for

  • Developers building generative AI applications who want prompt and model settings separate from application code.
  • Teams that want to version and iterate on AI behavior in configuration files.
  • Python or Node developers who want to use configured prompts from application code.

Documented uses

  • Keep prompts, model choices and model parameters in a version-controllable JSON file.
  • Create and edit prompts, including chained prompts with variables, in the editor.
  • Load and run configured prompts from Python or Node application code.
  • Save model-run outputs into an updated configuration file.
Before you choose

Requirements & limits

The project is open source under the MIT license. The README documents Python and Node package installation and a VS Code editor extension.

  • The configuration format is JSON-serializable and is intended to be version controlled.
  • The editor workflow requires the Python package, even when the Node SDK is used in application code.
  • The documented OpenAI quickstart requires an OpenAI API key.

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 Python package and open the local editor

Set up the documented command-line editor workflow for editing an AIConfig file.

Before you start

  • Python package installation with pip3
  • An OpenAI API key for the documented OpenAI quickstart

Steps

  1. Install the package with the command below.

    Documented command
    pip3 install python-aiconfig

  2. Set OPENAI_API_KEY to your OpenAI API key.

  3. Run aiconfig edit --aiconfig-path=travel.aiconfig.json to open that configuration in the editor.

Expected outcome

The local editor opens with the selected configuration's prompts, chaining logic and settings; edits are reflected in the AIConfig JSON file.

Guide limitations

  • The editor auto-saves every 15 seconds, with a manual Save button also available.
  • The documented API-key setup is for OpenAI.
Documentation 1 ↗
Source-based practical guide

Install the SDKs for application use

Install the documented Python or Node package for interacting with AIConfig from application code.

Before you start

  • Python with pip3 or Poetry, or Node.js with npm or Yarn
  • Install the Python AIConfig package as well if using AIConfig Editor to create or iterate on prompts

Steps

  1. For Python, install with the command below or poetry add python-aiconfig.

    Documented command
    pip3 install python-aiconfig

  2. For Node.js, install with the command below or yarn add aiconfig.

    Documented command
    npm install aiconfig

Expected outcome

The selected language package is installed for working with AIConfig in application code.

Guide limitations

  • The README's Node SDK note still requires installing the Python package when using the editor to create and iterate on prompts.
Documentation 1 ↗
Evidence and transparency

Sources & review

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