GH Repository · zai-org
CogAgent
An open-sourced end-to-end VLM-based GUI Agent
- stars
- 1,197
- 30-day movement
- +10/day
- Related entries
- 60
- Connections
- 1
pythonagent-appPythonagentvlmcomputer-useglmgui-agent
CogAgent is an open-source, end-to-end GUI agent built on a vision-language model, released by the zai-org GitHub organization. It is written in Python and licensed under Apache-2.0.
You want an open VLM-based agent that operates graphical user interfaces rather than only text.
Use it to
- Automate tasks in a GUI via computer use
- Experiment with VLM-driven agents
- Build on an open agent codebase
- Study end-to-end GUI agent design
For Developers and researchers building GUI agents
- Role
- agent-app
- Language
- Python
- Licence
- Apache-2.0
- Forks
- 101
- Open issues
- 28
- Last push
- 2025-04-04
topicsgui-agentcomputer-usevlmagentpythonopen-source