# AgentScope Studio — Agent Tracing UI > AgentScope Studio is a local visualization toolkit: Projects/Runs UI, OpenTelemetry-based tracing, and eval dashboards for AgentScope agents. ## Install Copy the content below into your project: ## Quick Use ```bash npm install -g @agentscope/studio as_studio ``` ## Intro AgentScope Studio is a local visualization toolkit: Projects/Runs UI, OpenTelemetry-based tracing, and eval dashboards for AgentScope agents. - **Best for:** Developers who need trace + eval visibility while iterating on agents - **Works with:** Node.js 20+; npm 10+; optional Docker; integrates with AgentScope (per README) - **Setup time:** 10–30 minutes ## Practical Notes - GitHub: 542 stars · 57 forks; pushed 2026-03-06 (verified via GitHub API). - README recommends Node.js >=20 and provides an npm global install with a single `as_studio` entrypoint. - README highlights OpenTelemetry tracing and evaluation analysis as first-class UI features. ## Main Make the UI actionable, not decorative: 1. Define a “run” contract: inputs, tools allowed, timeouts, and environment. 2. Capture traces for every run and keep them searchable by version (prompt/model/agent code). 3. Add simple evals (pass/fail rubrics) and correlate them with trace patterns (retries, tool failures, long spans). 4. Use the UI to produce a reproducible bug report: trace link + inputs + expected vs actual. This is how agent debugging becomes engineering work instead of guesswork. ### FAQ **Q: Do I need to use AgentScope?** A: README positions it as AgentScope-focused, but the tracing concepts are OpenTelemetry-based. **Q: Is Docker required?** A: No—README lists Docker as optional; the recommended install is via npm. **Q: What should I track first?** A: Start with latency and tool failures, then add token usage and cost annotations. ## Source & Thanks > Source: https://github.com/agentscope-ai/agentscope-studio > License: Apache-2.0 > GitHub stars: 542 · forks: 118 --- ## 快速使用 ```bash npm install -g @agentscope/studio as_studio ``` ## 简介 AgentScope Studio 是面向 agent 开发的本地可视化工具:提供项目/运行管理界面、基于 OpenTelemetry 的 tracing 展示,以及评测分析面板,适合把 agent 调试流程标准化。 - **适合谁:** 需要 tracing + 评测可视化来迭代 agent 的开发者 - **可搭配:** Node.js 20+;npm 10+;可选 Docker;与 AgentScope 集成(见 README) - **准备时间:** 10–30 分钟 ## 实战建议 - GitHub:542 stars · 57 forks;最近更新 2026-03-06(GitHub API 验证)。 - README 推荐 Node.js >=20,并提供 npm 全局安装与 `as_studio` 一键启动。 - README 将 OpenTelemetry tracing 与评测分析作为核心能力展示。 ## 主要内容 让可视化真正服务工程: 1. 先定义“Run”契约:输入、允许的工具、超时与运行环境。 2. 每次 run 都采集 trace,并按版本(prompt/model/agent 代码)可检索。 3. 加入最小可用的评测(通过/失败),并把结果与 trace 模式关联(重试次数、工具失败、长耗时 span)。 4. 用 UI 输出可复现 bug report:trace 链接 + 输入 + 期望/实际差异。 这样 agent 调试就从“玄学”变成可复现的工程工作。 ### FAQ **必须配合 AgentScope 吗?** 答:README 以 AgentScope 为主,但 tracing 思路基于 OpenTelemetry,可迁移到其他栈。 **一定要 Docker 吗?** 答:不一定。README 写 Docker 为可选,推荐 npm 安装。 **第一步该追踪什么?** 答:先看延迟与工具失败,再逐步加入 token 与成本标注。 ## 来源与感谢 > Source: https://github.com/agentscope-ai/agentscope-studio > License: Apache-2.0 > GitHub stars: 542 · forks: 118 --- Source: https://tokrepo.com/en/workflows/agentscope-studio-agent-tracing-ui Author: Agent Toolkit