midscene

About midscene

GUI Agent for E2E Testing

browser-use computer-use e2e-testing gpt-operator gui-agent javascript phone-use testing

Quick Facts

Stars	14,656
Forks	1,127
Language	TypeScript
Category	Agent Tool
License	MIT
Quality Score	50.9157470590271/100
Open Issues	99
Last Updated	2026-08-21
Created	2024-07-23
Platforms	browser, node
Est. Tokens	~13k

Compatible Skills

These tools work well together with midscene for enhanced workflows:

UI-TARS-desktop — semantic(0.38)+complementary+rare_topics+same_lang+similar_pop+shared_platform (72%)
TuriX-CUA — semantic(0.49)+complementary+rare_topics+similar_pop+shared_platform (66%)
agent-device — semantic(0.29)+complementary+rare_topics+same_lang+similar_pop+shared_platform (65%)
agent-device — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)

More Agent Tool Tools

Explore other popular agent tool tools:

superpowers ⭐ 276.4k
skills ⭐ 210.1k
AutoGPT ⭐ 186.8k
ollama ⭐ 179.2k
langflow ⭐ 153.6k
langchain ⭐ 144.8k
awesome-llm-apps ⭐ 133.6k
gstack ⭐ 129.2k
browser-use ⭐ 110.1k
ponytail ⭐ 98.3k

View all Agent Tool tools →

Popular TypeScript Agent Tools

openclaw ⭐ 387.2k · Codex Skill
n8n ⭐ 202.1k · MCP Server
dify ⭐ 153.3k · MCP Server
gstack ⭐ 129.2k · Agent Tool
gemini-cli ⭐ 106.6k · MCP Server

Frequently Asked Questions

What is midscene?

midscene is GUI Agent for E2E Testing. It is categorized as a Agent Tool with 14.7k GitHub stars.

What programming language is midscene written in?

midscene is primarily written in TypeScript. It covers topics such as browser-use, computer-use, e2e-testing.

How do I install or use midscene?

You can find installation instructions and usage details in the midscene GitHub repository at github.com/web-infra-dev/midscene. The project has 14.7k stars and 1127 forks, indicating an active community.

What license does midscene use?

midscene is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools