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

Coze Studio

An open-source AI agent development framework with visual tools for building, debugging, and deploying agents, apps, and workflows.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Coze 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 an agent project needs a visual development environment that combines workflows and supporting resources with self-hosted deployment and integration interfaces.

Who it is for

  • Developers building AI agents or agent-powered applications.
  • Teams seeking a self-hosted environment for agent development.
  • Users who want visual, no-code, or low-code workflows alongside customizable source code.

Documented uses

  • Create, publish, and manage AI agents.
  • Build applications and business logic through workflows.
  • Configure prompts, RAG resources, plugins, knowledge bases, databases, and models.
  • Expose conversations and workflows through OpenAPI or the Chat SDK.
  • Run and customize an agent development environment locally or on a server.
Before you choose

Requirements & limits

The documented open-source quickstart describes local deployment with Docker and Docker Compose, followed by account registration. The repository is public and licensed under Apache-2.0.

  • Local setup requires Docker, Docker Compose, and at least 2 CPU cores with 4 GB of memory.
  • A model service must be configured before models can be selected when building agents, workflows, or apps.
  • Official plugins require configuration and authentication keys for third-party services.
  • The platform includes OpenAPI and Chat SDK options for integrating agents or apps into another application.
  • Public-network deployments require security review because the project documents risks involving registration, workflow code execution, server configuration, SSRF, and API privileges.

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

Deploy Coze Studio locally and configure a model

Set up the open-source service locally and reach the workspace with a configured model service.

Before you start

  • A machine with at least 2 CPU cores and 4 GB of memory.
  • Docker and Docker Compose installed, with Docker running.
  • The Coze Studio source code.

Steps

  1. Retrieve the source code from the repository.

  2. For macOS or Linux, enter the project directory and run the documented make web command; for Windows, copy docker/.env.example to docker/.env and start the documented Docker Compose file.

  3. Register an account at http://localhost:8888/sign.

  4. Open the model-management page at http://localhost:8888/admin/#model-management and add a model whose image version is at least 0.5.0.

  5. Visit http://localhost:8888/ to open Coze Studio.

Expected outcome

A local Coze Studio service is started and a model is configured for use in agents, workflows, or apps.

Guide limitations

  • The first deployment may take time while images are retrieved and local images are built.
  • The documented setup does not by itself describe creation or deployment of a finished agent.
  • Public-network deployment requires separate security assessment and protective measures.
  • Official plugins require plugin configuration and authentication keys for third-party services.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
coze-dev/coze-studio · Official homepage title · retained in its source language
How we review sourcesSuggest a correction