Skip to content

armgit / cua

Public Imported from GitHub
0

Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.

document cloud vlm models

Sarina Li3b2722ad8ab9
diff --git a/README.md b/README.md
index 4b46c9f161..57c0d0d098 100644
--- a/README.md
+++ b/README.md
@@ -219,21 +219,22 @@ These are the valid model configurations for `ComputerAgent(model="...")`:
The following table shows which capabilities are supported by each model:
-| Model | Computer-Use | Grounding | Tools | VLM |
-| -------------------------------------------------------------------------------------------------------------------------------- | :----------: | :-------: | :---: | :-: |
-| [Claude Sonnet/Haiku](https://docs.claude.com/en/docs/agents-and-tools/tool-use/computer-use-tool#how-to-implement-computer-use) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ |
-| [OpenAI CU Preview](https://platform.openai.com/docs/models/computer-use-preview) | πŸ–₯️ | 🎯 | | πŸ‘οΈ |
-| [Qwen3 VL](https://huggingface.co/collections/Qwen/qwen3-vl) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ |
-| [GLM-V](https://huggingface.co/THUDM/glm-4v-9b) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ |
-| [Gemini CU Preview](https://ai.google.dev/gemini-api/docs/computer-use) | πŸ–₯️ | 🎯 | | πŸ‘οΈ |
-| [InternVL](https://huggingface.co/OpenGVLab/InternVL3_5-1B) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ |
-| [UI-TARS](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ |
-| [UI-TARS-2](https://cua.ai/dashboard/vlm-router) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ |
-| [OpenCUA](https://huggingface.co/xlangai/OpenCUA-7B) | | 🎯 | | |
-| [GTA](https://huggingface.co/HelloKKMe/GTA1-7B) | | 🎯 | | |
-| [Holo](https://huggingface.co/Hcompany/Holo1.5-3B) | | 🎯 | | |
-| [Moondream](https://huggingface.co/moondream/moondream3-preview) | | 🎯 | | |
-| [OmniParser](https://github.com/microsoft/OmniParser) | | 🎯 | | |
+| Model | Computer-Use | Grounding | Tools | VLM | Cloud |
+| -------------------------------------------------------------------------------------------------------------------------------- | :----------: | :-------: | :---: | :-: | :---: |
+| [Claude Sonnet/Haiku](https://docs.claude.com/en/docs/agents-and-tools/tool-use/computer-use-tool#how-to-implement-computer-use) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ | ☁️ |
+| [Claude Opus](https://docs.claude.com/en/docs/agents-and-tools/tool-use/computer-use-tool#how-to-implement-computer-use) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ | ☁️ |
+| [OpenAI CU Preview](https://platform.openai.com/docs/models/computer-use-preview) | πŸ–₯️ | 🎯 | | πŸ‘οΈ | |
+| [Qwen3 VL](https://huggingface.co/collections/Qwen/qwen3-vl) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ | ☁️ |
+| [GLM-V](https://huggingface.co/THUDM/glm-4v-9b) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ | |
+| [Gemini CU Preview](https://ai.google.dev/gemini-api/docs/computer-use) | πŸ–₯️ | 🎯 | | πŸ‘οΈ | |
+| [InternVL](https://huggingface.co/OpenGVLab/InternVL3_5-1B) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ | |
+| [UI-TARS](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ | |
+| [UI-TARS-2](https://cua.ai/dashboard/vlm-router) | πŸ–₯️ | 🎯 | πŸ› οΈ | πŸ‘οΈ | ☁️ |
+| [OpenCUA](https://huggingface.co/xlangai/OpenCUA-7B) | | 🎯 | | | |
+| [GTA](https://huggingface.co/HelloKKMe/GTA1-7B) | | 🎯 | | | |
+| [Holo](https://huggingface.co/Hcompany/Holo1.5-3B) | | 🎯 | | | |
+| [Moondream](https://huggingface.co/moondream/moondream3-preview) | | 🎯 | | | |
+| [OmniParser](https://github.com/microsoft/OmniParser) | | 🎯 | | | |
**Legend:**
@@ -241,6 +242,7 @@ The following table shows which capabilities are supported by each model:
- 🎯 **Grounding**: UI element detection and click coordinate prediction
- πŸ› οΈ **Tools**: Support for function calling beyond screen interaction
- πŸ‘οΈ **VLM**: Vision-language understanding
+- ☁️ **Cloud**: Supported on Cua VLM
**Composition Examples:**
@@ -381,6 +383,20 @@ Learn more in the [SOM documentation](./libs/python/som/README.md).
## 2025
+### December 2025
+
+- **Cloud VLM Platform**: Support for Claude Opus, Qwen3 VL 235B, and UI-TARS-2 on Cua VLM cloud infrastructure
+- **QEMU Container Support**: Native Linux and Windows container execution via QEMU virtualization
+
+### November 2025
+
+- **Generic VLM Provider**: Expanded support for custom VLM providers and model configurations
+- **NeurIPS 2025**: Coverage of computer-use agent research papers and developments ([Blog Post](https://cua.ai/blog/neurips-2025-cua-papers))
+
+### October 2025
+
+- **Agent SDK Improvements**: Enhanced model support and configuration options
+
### September 2025
- **Hack the North Competition**: First benchmark-driven hackathon track with guaranteed YC interview prize. Winner achieved 68.3% on OSWorld-Tiny ([Blog Post](https://www.cua.ai/blog/hack-the-north))