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

Agentok Studio

Agentok Studio is a visual development environment for designing multi-agent applications with AG2. It lets builders arrange agent workflows, configure tools and generate native Python code targeting AG2 v1.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agentok Studio — 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 it when you want a diagram-based way to author an AG2 agent application and inspect the code it produces. Check node support first if adapting an older AutoGen workflow.

Who it is for

  • Developers who want to compose AG2 multi-agent workflows visually.
  • Builders who need to configure tools and inspect generated code or execution logs.

Documented uses

  • Arrange agents and their conversation relationships in a visual workflow.
  • Configure tools and variables for use in a workflow.
  • Generate Python code for AG2 v1.
  • Inspect the workflow data and AG2 output and error logs.
Before you choose

Requirements & limits

The online Studio quickstart requires signing in with GitHub, Google or email. The project warns that its hosted deployment is not intended for production use.

  • Code generation targets AG2 v1, not the classic autogen or ConversableAgent stack.
  • Captain, Nested Chat, Retrieve and GPT Assistant are among the legacy node types listed as unsupported for code generation.
  • RAG has been removed from the project.
  • Local development involves a Next.js frontend and Python API; the backend instructions use Poetry, and LLaVA agent functionality requires a Replicate API token.

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

Start a project in the hosted Studio

Open the sample workflow and begin a conversation in Agentok Studio.

Before you start

  • A GitHub, Google or email sign-in

Steps

  1. Visit https://studio.agentok.ai and sign in.

  2. Choose Create New Project.

  3. Open the Chat tab in the new project to begin the conversation.

Expected outcome

A new project with a sample workflow, ready to explore in the Chat tab.

Guide limitations

  • The hosted deployment is not intended for production use.
  • Service levels are not guaranteed, and stored data may be wiped due to breaking changes.
Documentation 1 ↗
Source-based practical guide

Set up the frontend for local development

Prepare and start the Agentok Studio frontend development server.

Before you start

  • The Agentok repository
  • pnpm
  • Frontend environment values configured in .env.local

Steps

  1. Change to the frontend directory.

  2. Copy .env.sample to .env.local and configure the variables.

  3. Install dependencies with pnpm install.

  4. Start the development server with pnpm dev.

Expected outcome

The frontend development server is started using the documented command.

Guide limitations

  • The README notes that removing --turbo from the dev command in package.json may help if frequent useContext-related server errors occur.
  • The instructions cover frontend setup, not a complete local backend deployment.
Documentation 1 ↗
Evidence and transparency

Sources & review

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