📘 Official documentation

CAWRA IDE user manual

Practical guide to install CAWRA IDE, configure AI providers (Grok, OpenAI, Anthropic, Gemini, or Ollama), role routing, and use Chat, Task orchestrator, Repair and all integrated tools.

1. What is CAWRA IDE?

CAWRA IDE is a Windows development environment based on VSCodium (a fork of Visual Studio Code) with the native CAWRA AI extension preinstalled. Unlike an editor with a simple side chat, CAWRA includes:

The IDE is free; you only need to register on the website to download the installer. AI usage is billed to the account of the provider you choose (xAI, OpenAI, Anthropic, Google, etc.) with your own API key. Local models with Ollama have no cloud cost.

2. Installation (Windows)

  1. Register and download
    Visit the main page, register with your name and email, and download the .exe installer from the registration section.
  2. Run the installer
    Follow the installation wizard. CAWRA IDE installs as a standalone application; it does not replace VS Code if you already have it.
  3. Open a project
    Use File → Open Folder to open your repository. Many features (@path references, terminal, indexing) require an open workspace.
  4. Configure your AI provider
    On first launch, CAWRA will ask you to configure at least one API key. Follow the next section before using Chat or Task.
Recommended requirements
Windows 10/11, 8 GB RAM (16 GB recommended for large Tasks), Internet connection for your chosen provider's API, and Node.js/Python/Git depending on your projects.

3. Getting started: providers and API keys

CAWRA IDE 1.5 supports multiple AI providers. Configure the API keys for the ones you want to use; they are stored securely in the IDE's SecretStorage (not in settings.json).

3.1 Supported providers

ProviderFeatured modelsWhere to get the key
xAI / GrokGrok 4.5, 4.3, 4.20, Grok Buildconsole.x.ai
OpenAIGPT 5.6 Sol, Terra, Lunaplatform.openai.com
AnthropicFable 5, Sonnet 5, Opus 4.8console.anthropic.com
Google GeminiGemini 3 Pro, 3.5 Pro, 3.5 Flashaistudio.google.com
Ollama (local)Llama 3.1, Qwen 2.5, Code LlamaLocal installation — no cloud key

3.2 Configuring keys in CAWRA IDE

Open the CAWRA: Providers & models panel or the CAWRA Hub:

MethodHow to access
Providers panel Ctrl+Shift+P → CAWRA: Providers & models
CAWRA Hub Click ⚙ CAWRA in the status bar → Providers & models
CAWRA AI menu Gear icon → CAWRA AI submenu → Providers & models

Paste each key in its (hidden) field. You will see a confirmation when it is saved correctly.

3.3 Role-based routing and fallback

In the same panel you can choose which model each role uses (planner, executor, chat, vision, inline…) and set a fallback provider in case the primary one fails.

3.4 Verifying the connection

  1. Open the Chat panel (Chat tab in CAWRA AI).
  2. Write a simple message: «Hi, is the AI working?»
  3. If the key is valid, you will get a reply within seconds. If it is missing or incorrect, CAWRA will ask you to configure it.

4. IDE interface

CAWRA keeps the familiar VS Code layout with these proprietary elements:

5. CAWRA AI Hub

The Hub is CAWRA's control center. Open it with a click on ✦ CAWRA in the status bar or with the ⚙ CAWRA button inside Chat/Task.

Available options:

Busy state
If CAWRA is processing a Chat, Task, or Repair, the Hub shows a notice and does not allow opening other actions until it finishes. The status bar shows the spinning icon.

6. Providers, models, and routing

CAWRA 1.5 is multi-provider. The ModelRouter assigns the right model to each task based on its role, whichever providers you have configured:

Planner / Brain
Grok 4.5 · Claude Sonnet 5 · GPT Terra

Planning, task analysis, decomposition into subtasks.

Executor / Build
Grok Build · GPT Sol · Claude Fable

Code implementation, file editing, terminal tools.

Chat (Ask)
The model you choose per provider

Conversation, explanations, and questions without tools (Ask mode).

Inline
Gemini 3.5 Flash · Grok mini · local Ollama

Ghost-text autocomplete in the editor with minimal latency.

Vision
Gemini 3 Pro · Grok Vision · GPT Luna

Images in Chat, mockups, error screenshots, UI visual verification.

Enhancer
Gemini Flash · Grok mini

Automatic prompt enhancement before sending (optional in Chat).

Providers & models panel

Open CAWRA: Providers & models from the palette or the Hub to:

Models by role (Task and agents)

Configure them in Hub → Advanced models or in Settings by searching for cawra.models:

7. Advanced settings

Open File → Preferences → Settings and search for CAWRA AI, or use Hub → CAWRA Settings.

LLM parameters

Context and indexing

Task quality

Chat and images

Project file cawra.config.json

You can place a cawra.config.json file in the workspace or IDE root for default LLM, inline, chat, and context values. User settings in Configuration take priority over the file.

8. Changing the interface language

CAWRA IDE supports three interface languages:

How to change the language

  1. Open the global CAWRA AI menu (gear icon, bottom-left bar).
  2. Choose Idioma / Language / 语言 or directly English, Español, or 中文.
  3. You can also use the palette: Ctrl+Shift+P → CAWRA: Idioma / Language / 语言.
  4. CAWRA saves the preference in the user profile's locale.json and will prompt you to Restart now to apply the change. Accept the window restart.
Note
The language affects the IDE interface (menus, CAWRA messages). Chat responses may still follow the language you write in; the default system prompt is in Spanish.

9. Chat panel

Chat is your interactive assistant in the CAWRA AI side panel → Chat. It supports project context, images, file references, and — in advanced modes — real execution in the terminal.

Working modes

ModeWhat it doesWhen to use it
Ask A single LLM call. Answers questions and may suggest files, but does not run the terminal or use agent tools. Explanations, conceptual questions, idea review.
Edit AgentLoop with file tools: read_file, write_file, edit_file, list_dir. No terminal. Refactors, create/edit files without compiling or installing.
Agent Full AgentLoop: files + run_terminal, git_status, run_tests, etc. Compile, install dependencies, run tests, deploy.
Smart auto-escalation
If you write in Ask or Edit mode phrases like «build the app», «run gradlew», or «install npm», CAWRA automatically escalates to Agent mode for that turn and runs the commands in the CAWRA AI terminal.

Chat elements

Send messages with the Send button or Ctrl+Enter.

10. Task (Orchestrator)

Task is CAWRA's differentiator: you describe a high-level goal and the orchestrator breaks it down, plans a DAG of subtasks, assigns the most suitable model to each phase, and executes in parallel when possible.

Typical flow

  1. Analysis — Understands the open project, dependencies, and the goal (with images if you attach them).
  2. Planning — The Planner (e.g. Grok 4.5 or Claude Sonnet 5) generates subtasks with dependencies.
  3. Execution — One or more Executors (e.g. Grok Build or GPT Sol) implement each subtask with code and terminal tools.
  4. Verification — QA, optional tests, and visual verification on web projects.
  5. Delivery — Final summary with modified files and outcome.

How to launch a Task

Write the goal in natural language. Examples:

Tasks are queued if one is already running (cawra.queue.maxConcurrent controls concurrency). You can open the Agent Graph (Ctrl+Shift+G) to see live progress.

11. Repair

The Repair panel is focused on fixing errors: failed builds, broken tests, runtime exceptions. CAWRA analyzes the error context and proposes an automatic repair plan similar to Task but focused on resolving the specific failure.

Open it from CAWRA AI → Repair tab or with the command CAWRA: Abrir Repair.

12. Audit

Audit records the history of agent actions: subtasks, tools used, tokens consumed, and results. Useful for reviewing what the orchestrator did, exporting logs, or debugging complex tasks.

Access: CAWRA AI panel → Audit, or Hub → Audit.

13. Agent Graph

Interactive visualization of the current or completed Task. Shows phase nodes, subtasks, agents, and tools connected in an animated graph.

14. @file references and context

CAWRA injects project context automatically when you use mentions:

Adding references without typing

15. Images and vision

Both Chat and Task accept reference images:

Images are processed with the Vision model you have assigned (e.g. Gemini 3 Pro, Grok Vision or GPT Luna). Useful for UI mockups, error screenshots, diagrams, or designs the planner must follow.

Configurable limits: maximum 4 images and 5 MB each (by default).

16. Inline autocomplete and Composer

Ghost text (inline completion)

As you type, CAWRA suggests code in gray (ghost text) using the assigned inline model (e.g. Gemini 3.5 Flash, Grok mini or local Ollama).

Enable/disable with cawra.inlineEnabled. Fast mode: cawra.inline.fastMode.

Inline editing (Ctrl+K)

Select code in the editor and press Ctrl+K. Write the instruction (e.g. «convert to async/await») and CAWRA replaces the selection.

Composer / Agent Mode (Ctrl+I)

Ctrl+I opens the Composer for multi-file changes with agent planning, similar to the Cursor Agent flow.

Selection actions (right-click)

17. Codebase semantic index

CAWRA indexes your project so @codebase and the orchestrator can find relevant code without reading the entire repo.

18. Terminal and security

In Agent modes of Chat and during Tasks, CAWRA runs commands in the integrated CAWRA AI terminal.

Security controls

Common commands like gradlew, npm, git status are on the policy engine allowlist.

19. Remote work (SSH)

CAWRA includes Remote SSH support (based on Open Remote SSH):

The orchestrator and agents run on the remote server as if it were local. The CAWRA AI extension is installed automatically on the remote host.

19.1 ssh-agent service on Windows

If ssh-agent does not start (requires admin permissions), run the following once in PowerShell as administrator:

Set-Service ssh-agent -StartupType Automatic
Start-Service ssh-agent

After this, the SSH agent will start with Windows and can manage your private keys for public-key connections.

19.2 Configuring hosts in ~/.ssh/config

Use CAWRA: Configure SSH Hosts... or manually edit ~/.ssh/config on your local machine. Each Host block defines a server CAWRA can connect to via Open Remote Window or Connect to Host....

Public/private key connection

Recommended format when the server accepts SSH key authentication (no password on every connection):

Host SERVER_NAME
  HostName IP_OR_HOSTNAME
  User root
  IdentityFile ~/.ssh/name
  IdentitiesOnly yes

Username and password connection

Format for SSH password authentication (usually root user). CAWRA will prompt for the password when connecting:

Host HOST_NAME
  HostName IP_OR_HOSTNAME
  User root
  LocalForward 8080 /var/www/vhosts/
Connecting from CAWRA
  1. Configure the host in ~/.ssh/config using one of the formats above.
  2. Open the palette (Ctrl+Shift+P) and run CAWRA: Abrir ventana remota or CAWRA: Connect to Host....
  3. Select the alias (SERVER_NAME or HOST_NAME). If using a password, enter it when prompted.
  4. Open the project folder on the remote server (File → Open Folder).

20. Keyboard shortcuts

ShortcutAction
Ctrl+LOpen / focus Task
Ctrl+Shift+GAgent Graph
Ctrl+KInline editing (with selection)
Ctrl+IComposer / Agent Mode
Ctrl+Shift+EExplain selected code
TabAccept inline suggestion (ghost text)
EscapeDismiss inline suggestion
Alt+\Force inline autocomplete
Ctrl+EnterSend message in Chat / Task
Ctrl+Shift+PCommand Palette (all CAWRA commands)

21. Frequently asked questions

Is CAWRA IDE free?

Yes. The IDE and orchestrator are free. You only pay for API usage with the provider you choose, at their rates.

Can I use several providers at once?

Yes. CAWRA 1.5 is multi-provider: configure the API keys you need and the system will automatically route the best model for each role. You can also use Ollama locally with no cloud API cost.

Chat does not run terminal commands

Check that you are in Agent mode, or use execution verbs («build», «run»…) to trigger auto-escalation. Also verify that cawra.shell.enabled is active.

Where are my API keys stored?

In the VS Code/Codium secure secret store (SecretStorage), one key per provider. They are never saved in plain text in settings.json.

Does it work offline?

The editor yes; cloud AI features require a connection (except local Ollama). The semantic index and local editing work offline.

Is it compatible with VS Code extensions?

Yes. CAWRA uses Open VSX by default (https://open-vsx.org) and is compatible with most VS Code extensions.

Need help?
Visit the main page to register, download the latest version, or contact support.
Need help?

Visit the home page to register, download the latest version, or contact support.