V
VISUALSKILL
Hierarchical skill library for GUI automation with reusable multimodal interaction patterns
Open SourceFree
About
Research framework for organizing computer-use agent skills into reusable, application-specific components. Combines visual and textual artifacts in a hierarchical library structure with MCP-compatible interfaces. Enables agents to learn and reuse GUI interaction patterns across different applications, reducing the need to relearn common tasks. Particularly useful for building agents that automate desktop workflows and UI interactions.
Details
| Language | |
| Patterns |
Tags
frameworkopen-sourcemcpautonomoustool-usepython
Quick Info
- Organization
- Research Team (Jiang et al.)
- Pricing
- open-source
- Free Tier
- Yes
- Updated
- Jun 18, 2026
Also in Frameworks
L
LangChain
Build context-aware reasoning applications with LLMs
OSSFree
LangChain AI
139.6K850.0K/wtoday469
A
AutoGen
Microsoft's framework for building multi-agent AI systems
OSSFree
Microsoft
59.1K9w ago445
C
CrewAI
Multi-agent orchestration framework for collaborative AI workflows
OSSFree
CrewAI Inc
53.9Ktoday297