zai-org/CogAgent
An open-sourced end-to-end VLM-based GUI Agent observed · 2026-08-28
Health v2 · maintenance only
33/100
- Activity 14
- Release rhythm 35
- Longevity 72
Flags: no_releases
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 1009
- days_rel: n/a
- days_push: 516
- n_releases_24m: 0
Adoption not part of the score
1194 stars · 101 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
CogAgent is an open-source vision-language model (VLM) based GUI agent that understands screen captures and natural language to automate interactions with graphical user interfaces. It provides the CogAgent-9B model with bilingual (Chinese/English) support for GUI perception, reasoning, and action generation.
Use cases
- automate tasks on a computer screen with an AI agent
- build a GUI automation agent from screenshots
- understand and act on UI elements using a vision-language model
- control desktop applications with natural language commands
- run a computer-use agent open source
- parse screen captures to identify clickable UI elements
When to choose
- you need an open-source VLM agent for GUI automation
- you want bilingual Chinese/English screen understanding
- you're researching vision-language agents for computer use
When to avoid
- you need a lightweight model without GPU hardware
- you only need text-based automation without screen perception
- you need a production-ready commercial agent with support guarantees
Facets
library · maturity active
machine-learning computer-vision agent-framework llm-inference artificial-intelligence computer-vision large-language-models python vlm gui-agent computer-use screen-understanding glm cvpr ai-agents gpu linux
1 source
- readme: https://github.com/zai-org/CogAgent · fetched 2026-08-28 · ff64259dc60a
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| zai-org/CogAgent | main | 33 |
For agents
markdown · JSON · MCP: product_card(name="zai-org/CogAgent")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem