Computer-use agentsImage + text

CogAgent / AutoGLM

One of the first open models for controlling an interface from a screenshot; its successor, AutoGLM-Phone, works in Android smartphone apps.

Developer
Zhipu AI (Z.ai) and Tsinghua University, China
First release
Dec 2023
Latest release
Dec 2025
Sizes
9B – 18B
License
Commercial use with conditionsMixed: CogAgent-18B is Apache 2.0, CogAgent-9B has its own license (commercial use after registration), AutoGLM-Phone is MIT
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Software development, Retail and marketplaces
Deploy on your server Hugging Face GitHub

What it does

  • Automating actions in mobile apps
  • Working in web interfaces without an API
  • Testing apps against scenarios

Where it is used

Mobile development and testingBack officeE-commerce

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. AutoGLM-Phone-9B
  2. CogAgent-9B
  3. CogAgent-18B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can CogAgent / AutoGLM be used in a commercial project?

With conditions. License: Mixed: CogAgent-18B is Apache 2.0, CogAgent-9B has its own license (commercial use after registration), AutoGLM-Phone is MIT. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does CogAgent / AutoGLM need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does CogAgent / AutoGLM support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download CogAgent / AutoGLM and what does it cost?

The CogAgent / AutoGLM weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Computer-use agentsGUI-Owl / Mobile-AgentAlibaba (Tongyi Lab, X-PLUG) · ChinaCommercial use allowed

Models for controlling phones and computers from the Mobile-Agent project: they work with Android, Windows, macOS and the browser; version 1.5 has a reasoning mode.

DetailsComputer-use agentsUI-TARSByteDance Seed · ChinaCommercial use allowed

A model that looks at a screenshot and controls the mouse and keyboard itself: clicks, fills in fields, navigates menus. The first generation and 1.5-7B are open; UI-TARS-2 weights were not released.

DetailsImage + textCogVLM и GLM-VZhipu AI (Z.ai) and Tsinghua University · ChinaCommercial use allowed

Vision models from Zhipu: first CogVLM, then the GLM-V line. GLM-4.6V can call tools based on images and act as an agent operating an interface.

Details

Source: huggingface.co/zai-org/AutoGLM-Phone-9B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.