HanyuanWang/LiveStream-Agent-Studio

面向抖音直播电商的 Windows 本地 AI Agent Studio,贯通主播发现、直播洞察、直播复盘与短视频内容编导的统一智能工作流。

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

把主播发现、直播拆解、直播复盘和短视频编导放进一个统一入口。 Bring creator discovery, livestream breakdown, performance review, and short-form video planning into one unified workspace. LiveStream Agent Studio 是面向直播电商团队打造的 Windows 本地优先 AI Agent 工作台。 LiveStream Agent Studio is a local-first Windows AI Agent workspace built for livestream commerce teams. 本版本将主播发现、直播拆解、话术与流量复盘、短视频内容编导整合到统一入口,帮助直播运营、投放、内容和复盘团队,将榜单、录屏、逐字稿、流量数据与脚本资产沉淀为可追踪、可复用的完整工作流。 It brings creator discovery, livestream breakdown, speech-and-traffic review, and short-form video planning into a single interface. The goal is to help operations, media-buying, content, and review teams turn rankings, recordings, transcripts, traffic data, and scripts into traceable and reusable workflows. 这是项目的首个公开版本,适合体验、测试和内部研究使用。 This is the project's first public release. It is intended for evaluation, testing, and internal research. 管理关注领域、候选主播和达人研究任务,读取用户账号正常可见的蝉妈妈榜单或主播页面,生成结构化达人拆解,并将候选主播加入后续可选录制流程。 Manage research categories, candidate creators, and creator-analysis tasks. The Agent can read Chanmama rankings or creator pages normally visible to the signed-in user, generate structured creator profiles, and add selected creators to an optional recording workflow. 将完整直播视频转化为带秒级时间戳的结构化逐字稿,自动完成音频提取、云端转写和内容整理,并输出可继续分析的 Excel 文件。 Convert full-length livestream recordings into structured transcripts with second-level timestamps. The workflow…

HanyuanWang/LiveStream-Agent-Studio on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-10-29T12:31:29.314Z

Inside the original README — Document outline
  1. LiveStream Agent Studio
  2. 面向直播电商团队的 Windows 本地优先 AI 工作台
  3. A local-first AI workspace for livestream commerce teams on Windows
  4. ✨ 核心能力 Core Capabilities
  5. 01 · Creator Scout Agent|主播发现
  6. 02 · Live Breakdown Agent|直播拆解
  7. 03 · Live Review Agent|直播复盘
  8. 04 · Video Director Agent|短视频编导
  9. Unified Task Center|统一任务中心
  10. Local Settings Hub|本地设置中心
  11. 四个 Agent Four Agents
  12. 快速开始 Quick Start

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

面向抖音直播电商的 Windows 本地 AI Agent Studio,贯通主播发现、直播洞察、直播复盘与短视频内容编导的统一智能工作流。

Repository facts

Owner
HanyuanWang
Primary language
Python
Stars
1,022
Forks
170
Open issues + pull requests
12
License
MIT
Archived
No
Default branch
main
Created
2026-08-22T14:16:48.000Z
Last push
2026-08-24T02:48:43.000Z

Topics and intended use

Owner-supplied topics: ai-agent, douyin, livestream, speech-to-text

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-09-21T12:01:34.222Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent