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.

Fix the links to Claude's documentation in the documentation (#862)

João Palmeiroc791cb685238
diff --git a/blog/bringing-computer-use-to-the-web.md b/blog/bringing-computer-use-to-the-web.md
index da17abe51e..8c87d0b3c6 100644
--- a/blog/bringing-computer-use-to-the-web.md
+++ b/blog/bringing-computer-use-to-the-web.md
@@ -45,7 +45,7 @@ At the time of writing, the **computer-use-preview** model has limited availabil
- Cannot be used in the OpenAI Playground
- Outside of ChatGPT Operator, usage is restricted to the new **Responses API**
-Luckily, the `@trycua/computer` library can be used in conjunction with other models, like [Anthropic’s Computer Use](https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/computer-use-tool) or [UI-TARS](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B). You’ll just have to write your own handler to parse the model output for interfacing with the container.
+Luckily, the `@trycua/computer` library can be used in conjunction with other models, like [Anthropic’s Computer Use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) or [UI-TARS](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B). You’ll just have to write your own handler to parse the model output for interfacing with the container.
### Cua Cloud Containers
diff --git a/blog/build-your-own-operator-on-macos-2.md b/blog/build-your-own-operator-on-macos-2.md
index 3f339f8289..c350363b9f 100644
--- a/blog/build-your-own-operator-on-macos-2.md
+++ b/blog/build-your-own-operator-on-macos-2.md
@@ -163,7 +163,7 @@ The `cua-agent` framework provides multiple agent loop implementations to abstra
- **OpenAI Loop**: Uses the Responses API with a specific `computer_call_output` format for sending screenshots after actions. Requires handling safety checks and maintains a chain of requests using `previous_response_id`.
-- **Anthropic Loop**: Implements a [multi-agent loop pattern](https://docs.anthropic.com/en/docs/agents-and-tools/computer-use#understanding-the-multi-agent-loop) with a sophisticated message handling system, supporting various API providers (Anthropic, Bedrock, Vertex) with token management and prompt caching capabilities.
+- **Anthropic Loop**: Implements a [multi-agent loop pattern](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#understanding-the-multi-agent-loop) with a sophisticated message handling system, supporting various API providers (Anthropic, Bedrock, Vertex) with token management and prompt caching capabilities.
- **UI-TARS Loop**: Requires custom message formatting and specialized parsing to extract actions from text responses using a "box token" system for UI element identification.
@@ -191,7 +191,7 @@ The performance of different Computer-Use models varies significantly across tas
- **AgentLoop.OPENAI**: Choose when you have OpenAI Tier 3 access and need the most capable computer-use agent for web-based tasks. Uses the same [OpenAI Computer-Use Loop](https://platform.openai.com/docs/guides/tools-computer-use) as Part 1, delivering strong performance on browser-based benchmarks.
-- **AgentLoop.ANTHROPIC**: Ideal for users with Anthropic API access who need strong reasoning capabilities with computer-use abilities. Works with `claude-sonnet-4-5-20250929` and `claude-3-7-sonnet-20250219` models following [Anthropic's Computer-Use tools](https://docs.anthropic.com/en/docs/agents-and-tools/computer-use#understanding-the-multi-agent-loop).
+- **AgentLoop.ANTHROPIC**: Ideal for users with Anthropic API access who need strong reasoning capabilities with computer-use abilities. Works with `claude-sonnet-4-5-20250929` and `claude-3-7-sonnet-20250219` models following [Anthropic's Computer-Use tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#understanding-the-multi-agent-loop).
- **AgentLoop.UITARS**: Best for scenarios requiring more powerful OS/desktop, and latency-sensitive automation, as UI-TARS-1.5 leads in OS capabilities benchmarks. Requires running the model locally or accessing it through compatible endpoints (e.g. on Hugging Face).
@@ -677,6 +677,6 @@ With the basics covered, you might want to explore:
- [cua-agent GitHub repository](https://github.com/trycua/cua/tree/main/libs/python/agent)
- [Agent Notebook Examples](https://github.com/trycua/cua/blob/main/notebooks/agent_nb.ipynb)
- [OpenAI Agent SDK Specification](https://platform.openai.com/docs/api-reference/responses)
-- [Anthropic API Documentation](https://docs.anthropic.com/en/api/getting-started)
+- [Anthropic API Documentation](https://platform.claude.com/docs/en/api/overview)
- [UI-TARS GitHub](https://github.com/ByteDance/UI-TARS)
- [OmniParser GitHub](https://github.com/microsoft/OmniParser)
diff --git a/docs/content/docs/lume/examples/claude-code/sandbox.mdx b/docs/content/docs/lume/examples/claude-code/sandbox.mdx
index ae6b4a324f..b332c6bc88 100644
--- a/docs/content/docs/lume/examples/claude-code/sandbox.mdx
+++ b/docs/content/docs/lume/examples/claude-code/sandbox.mdx
@@ -5,7 +5,7 @@ description: Run Claude Code CLI safely in an isolated macOS VM
import { Callout } from 'fumadocs-ui/components/callout';
-Run [Claude Code](https://docs.anthropic.com/en/docs/claude-code) on your host while it executes commands inside a sandboxed macOS VM via SSH. No MCP required—just the `lume` CLI and SSH.
+Run [Claude Code](https://code.claude.com/docs) on your host while it executes commands inside a sandboxed macOS VM via SSH. No MCP required—just the `lume` CLI and SSH.
## Why sandbox Claude Code?
@@ -73,7 +73,7 @@ curl -fsSL https://claude.ai/install.sh | bash
brew install --cask claude-code
```
-See [Claude Code docs](https://docs.anthropic.com/en/docs/claude-code) for other installation methods.
+See [Claude Code docs](https://code.claude.com/docs) for other installation methods.
## Step 5: Use Claude Code with the sandbox
@@ -178,4 +178,4 @@ But it can:
- [Homebrew Testing](/lume/examples/claude-code/homebrew-testing) — Test packages in a clean environment
- [Claude Cowork with MCP](/lume/examples/claude-cowork/sandbox) — Use MCP for native VM integration
- [Unattended Setup](/lume/guide/fundamentals/unattended-setup) — Customize the VM configuration
-- [Claude Code docs](https://docs.anthropic.com/en/docs/claude-code) — Learn more about Claude Code's capabilities
+- [Claude Code docs](https://code.claude.com/docs) — Learn more about Claude Code's capabilities
diff --git a/libs/python/agent/agent/loops/anthropic.py b/libs/python/agent/agent/loops/anthropic.py
index 0fa08b9691..4da1f77f05 100644
--- a/libs/python/agent/agent/loops/anthropic.py
+++ b/libs/python/agent/agent/loops/anthropic.py
@@ -683,7 +683,7 @@ def _convert_completion_to_responses_items(response: Any) -> List[Dict[str, Any]
action_type = tool_input.get("action")
# Action reference:
- # https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/computer-use-tool#available-actions
+ # https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#available-actions
try:
# Basic actions (all versions)