midscene
Automate and test visible interfaces with natural-language instructions.
- Stars
- 14,065
- Forks
- 1,071
- License
- MIT
Start with a real need, then filter by use case, format, runtime, and repository facts to find projects you can use, combine, or build on.
Automate and test visible interfaces with natural-language instructions.
Translate, polish, and summarize selected text from a browser or desktop app.
Manage multi-chain crypto assets across mobile, desktop, web, and browser extensions.
Detect and translate text inside comics across common image and archive formats.
Manage Elasticsearch clusters, indices, and documents through a graphical interface.
Generate and export OpenAPI 3.1 specifications from live browser network traffic.
Generate OpenAPI 3.1 specifications from live traffic or HAR files.
Run page-aware AI tasks with multiple models, Agent Skills, and MCP from a browser sidebar.
Use a local IPFS node directly from a web browser
Save links, notes, and images offline in searchable local vaults.