coze-dev /coze-loop
Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.
★ 5,800⑂ 804👁 33⑃ 587● 110▤ 8
+0
日增长
5,800
stars
804
forks
33
watchers
587
prs
110
issues
8
releases
README
!Image
Coze Loop •
Feature list •
Quick start •
Developer guide
English | 中文
What is Coze Loop
Coze Loop is a developer-oriented, platform-level solution focused on the development and operation of AI agents. It addresses various challenges faced during the AI agent development process, providing full lifecycle management capabilities from development, debugging, evaluation, to monitoring.
Based on the commercial version, Coze Loop introduces an open-source edition that offers developers free access to core foundational feature modules. By sharing its core technology framework in an open-source model, developers can customize and extend according to business needs, facilitating community co-construction, sharing, and exchange, helping developers participate in AI agent exploration and practice with zero barriers.
What can Coze Loop do?
Coze Loop helps developers develop and operate AI Agent more efficiently by providing full lifecycle management capabilities. Whether it is prompt engineering, AI Agent evaluation, or monitoring and optimization after deployment, Coze Loop provides powerful tools and intelligent support, greatly simplifying the development process of AI Agents and enhancing their operational performance and stability.
Prompt development: The Prompt development module of Coze Loop provides developers with end-to-end support for writing, debugging, optimizing, and version management. Through a visual Playground, it enables real-time interactive testing of prompts, allowing developers to intuitively compare the output of different LLMs.
Evaluation: The Coze Loop evaluation module provides developers with systematic evaluation capabilities, enabling automated multi-dimensional testing of prompts and Coze agents' output, such as accuracy, conciseness, compliance, and more.
Observability: Coze Loop provides developers with observability for the entire execution process, fully recording every stage from user input to AI output, including key stages such as prompt parsing, model invocation, and tool execution, and automatically capturing intermediate results and exceptions.
Feature list
| Feature | Functional points |
| --- | --- |
| Prompt debugging | Playground debugging and comparison Prompt version management |
| Evaluation | Manage evaluation sets Management evaluator Manage experiments |
| Observation | SDK trace reporting Trace data observation |
| Model | Support integration with OpenAI, Volcengine Ark, and other models |
Quick Start
Refer to Quick Start to learn in detail how to install and deploy the latest version of Coze Loop.
Deployment method 1: Docker deployment (Docker Compose)
Please install and start Docker Engine before you start.
Procedure:
1. Clone the source code.
Run the following command to obtain the latest version of the Coze Loop source code.
Bash
Clone the code
git clone https://github.com/coze-dev/coze-loop.git
Enter the coze-loop directory
cd Top issues
#111Is there currently a 100 second timeout limit for a single call? The data in my experiment showed that failures occurred after 1.67 minutes10 comments · 2025-08-19#95[BUG] The gpt5 model of openai is not supported yet7 comments · 2025-08-10#115[BUG] modified FrontEnd static files not working5 comments · 2025-08-20#257[BUG]For the source-deployed coze-loop using the Deepseek-v3 model to build an evaluator, an error occurs when using the evaluator.4 comments · 2025-10-24#167[BUG] Can the retention period of CozeLoop’s trace be extended beyond 7 days?4 comments · 2025-09-09#136[BUG] can not docker pull cozedev/coze-loop:1.2.03 comments · 2025-08-29#108[FEATURE] Can I use API calls to operate the evaluation process3 comments · 2025-08-15#91[BUG]The failed task remained in the "Pending" status after retrying and was never executed.3 comments · 2025-08-08
Discussions
#443For deployments using docker-compose, how can changes to the frontend and backend source code be made effective?0 comments · 2026-03-03#406使用代理在wsl的ubuntu24中安装docker的cozeloop出现问题0 comments · 2026-01-26#356How can I upload other types of attachments, such as CSV files?0 comments · 2025-12-22#339[Question] How can I get the hidden trace_id ?0 comments · 2025-12-09#313coze-loop可以监测coze中的工作流吗0 comments · 2025-11-17#292The current Coze-loop SDK only has prompt and Trace functions, and does not support Agent, evaluation, or experimentation features. Will these features be added in future versions?1 comments · 2025-11-05#283Pyodide如何离线运行0 comments · 2025-11-03#273启动前端服务,在packges下的tsx文件中加载模块语句,地址中的'@'的语句都报错了0 comments · 2025-10-30
Latest release
v1.5.1 v1.5.1 2026-01-20Image Version cozedev/coze-loop:1.5.1 cozedev/coze-loop-python-faas:1.0.0 What's Changed [feat][all] Release 1.4.0 by @lsy357 in https://github.com/coze-dev/coze-loop/pull/230 [fix]auto task by @zero3233-bd in https://github.com/coze-dev/coze-loop/pull/232 [feat][frontend] code evaluator route by @wec4dre96-w in https://github.com/coze-dev/coze-loop/pull/231 [fix] auto task by @zero3233-bd in https://github.com/coze-dev/coze-loop/pull/235 [feat][all] release v1.4.1 by @lsy357 in https://github.com/coze-dev/coze-loop/pull/236 [feat][evaluation] custom target by @dsf86 in htt