# coze-dev/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.

Repository: https://github.com/coze-dev/coze-studio
Canonical: https://ross.abutalabs.com/products/coze-studio
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: agent, chatbot-framework, generative-ai, go, low-code-ai, multimodel-ai, coze-platform, workflow, agent-platform, ai-plugins, coze, rag, kouzi, no-code, studio, chatbot, typescript
Last push: 2026-07-29T03:18:43+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 69, longevity 31
- inputs: {"age_days": 434, "days_push": 35, "days_rel": 209, "gap_med": 9.5, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21506, forks 3124 (observed 2026-08-28T04:11:31.790741+00:00)

## What it is
Coze Studio is an open-source, all-in-one AI agent development platform with visual, no-code/low-code tools for building, debugging, and deploying agents, apps, and workflows. Its Go backend and React/TypeScript frontend are built on a microservices architecture with DDD principles, supporting models like OpenAI and Volcengine plus RAG, plugins, and knowledge bases.

## Use cases
- build a chatbot without writing code
- create AI agents with workflows and knowledge bases
- self-host an agent development platform
- build RAG applications over company documents
- develop and publish AI apps with plugins
- debug and deploy LLM-powered agents
- integrate multiple LLM providers in one platform

## When to choose
- you want a visual, low-code environment for building AI agents
- you need an all-in-one platform covering prompts, RAG, plugins, and workflows
- you want to self-host a Coze-like agent platform
- your team mixes developers and non-developers building AI apps

## When to avoid
- you only need a lightweight agent library or SDK to embed in code
- you require fully custom agent logic beyond visual workflow tools
- you cannot run Docker-based microservices infrastructure
- you need a managed SaaS solution rather than self-hosting

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, chatbot, workflow-automation, llm-inference, prompt-engineering, web-framework, self-hosted
- domain: large-language-models, chatbots, developer-tools, self-hosted
- platform: self-hosted, go, cross-platform
- tags: low-code, no-code, visual-builder, agent-platform, knowledge-base, plugins, microservices, ddd, openai, volcengine, ai-agents, retrieval-augmented-generation, docker, web-server, typescript

## Member repositories
- coze-dev/coze-studio (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:31.790741+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:58:05.242131+00:00, confidence not recorded.
  - readme: https://github.com/coze-dev/coze-studio (fetched 2026-08-28T04:11:31.790741+00:00, sha 604751464c28)
- Data as of 2026-08-30T08:39:29.467469+00:00.