coze-studio
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agen
What is coze-studio?
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
Overview of coze-studio
What it is
Coze Studio is an open-source all-in-one AI agent development tool. Its backend is developed using Golang, the frontend uses React + TypeScript, and the overall architecture is based on microservices and built following domain-driven design (DDD) principles.It provides the latest large models and tools, various development modes and frameworks. The tool is derived from the Coze Development Platform, which has served tens of thousands of enterprises and millions of developers. Coze Studio aims to lower the threshold for AI agent development and application.
Key features
- Model service: Manage the model list, integrate services such as OpenAI and Volcengine.
- Build agent: Build, publish, and manage agents; support configuring workflows, knowledge bases, and other resources.
- Build apps: Create and publish apps; build business logic through workflows.
- Build a workflow: Create, modify, publish, and delete workflows.
- Develop resources: Support creating and managing plugins, knowledge bases, databases, and prompts.
- API and SDK: Provide OpenAPI for conversations and chats; integrate agents or apps via Chat SDK.
Use cases
Coze Studio can be used to quickly build an AI assistant agent, develop agents with functions like knowledge and plugins to resolve model hallucination, develop workflows for business logic or specific tasks, and integrate agents or apps with local business systems through Chat SDK. It can also be used to implement various AI scenarios, such as building web-based online customer service.
Getting started
Environment requirements: 2 Core, 4 GB RAM; pre-install Docker and Docker Compose and start the Docker service.Bash# Clone codegit clone https://github.com/coze-dev/coze-studio.gitcd coze-studio# start service# for macOS or Linuxmake web# for windowscp ./docker/.env.example ./docker/.envdocker compose -f ./docker/docker-compose.yml upThen register an account at http://localhost:8888/sign, configure the model at http://localhost:8888/admin/#model-management, and visit Coze Studio at http://localhost:8888/.
License and pricing
This project uses the Apache 2.0 license. Pricing type is open source.
Based on the project's public README and repository metadata.