# zai-org/CogAgent

An open-sourced end-to-end VLM-based GUI Agent

Repository: https://github.com/zai-org/CogAgent
Canonical: https://ross.abutalabs.com/products/cogagent
Language: Python
License: Apache-2.0
License Family: permissive
Topics: gui-agent, computer-use, vlm, agent, glm
Last push: 2025-04-04T13:29:55+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 14, release rhythm 35, longevity 72
- inputs: {"age_days": 1009, "days_push": 516, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1194, forks 101 (observed 2026-08-28T04:03:56.683415+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, agent-framework, llm-inference
- domain: artificial-intelligence, computer-vision, large-language-models
- platform: python
- tags: vlm, gui-agent, computer-use, screen-understanding, glm, cvpr, ai-agents, gpu, linux

## Member repositories
- zai-org/CogAgent (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.683415+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:22:11.474381+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/CogAgent (fetched 2026-08-28T04:03:56.683415+00:00, sha ff64259dc60a)
- Data as of 2026-08-30T08:39:29.467469+00:00.