WorkspaceGPT VSCode Extension

🧩 New: WorkspaceGPT for Chrome — ask your Confluence & Azure DevOps questions from a browser side panel. Add to Chrome, then paste a share code from this extension (Settings → Share to Chrome).

Visit our homepage: workspacegpt.in

WorkspaceGPT is your AI-powered, RAG-based coding assistant designed specifically for your local development environment. It allows you to ask workspace-related questions and get precise answers — all from the comfort of your VSCode editor.

🔐 Flexible Privacy Options

WorkspaceGPT gives you control over your data privacy:

• 100% Local Operation: With Ollama provider, everything runs locally on your system with no data sent to third-party servers
• Cloud Provider Options: For enhanced capabilities, you can choose to use cloud-based providers like OpenAI, Gemini, Groq, Requestly, or OpenRouter
• You Choose: Select the privacy level that works for your needs while maintaining security

🧠 Features

• 🤖 AI-Powered Workspace Q&A: Get context-aware answers from your local workspace using Retrieval-Augmented Generation (RAG)
• 📄 Confluence One-Click Integration: Seamlessly connect to your Confluence space and chat with your documentation with just one click
• 🔷 Azure DevOps (ADO) Support: Deep integration with ADO to track work items, pull requests, and synchronize relevant context directly
• 🧭 Smart Code Navigation: Understand and explore your codebase more efficiently (coming soon!)
• 💬 Interactive Chat Interface: Ask questions and receive intelligent, project-specific responses
• ⚡ Runs Locally: No remote APIs. Zero data leakage. Total privacy.

🚀 Getting Started

Prerequisites

No specific prerequisites required! WorkspaceGPT now supports multiple AI providers:

1. Ollama - For 100% local operation
2. OpenAI - For powerful cloud-based models
3. Gemini - Google's advanced AI models
4. Groq - High-performance inference
5. Requestly - Custom API integration
6. OpenRouter - For access to multiple models

🧠 Default Model

By default, WorkspaceGPT uses a lightweight model: llama3.2:1b when using Ollama. If you're looking for more accurate and context-rich responses, you can switch to a more capable model that fits your system — such as llama3.2:4b, gemma3:4b, or mistral, or choose one of our cloud provider options.

Installation

1. Open Visual Studio Code
2. Navigate to the Extensions view (Ctrl+Shift+X or Cmd+Shift+X on macOS)
3. Search for "WorkspaceGPT"
4. Click Install

🛠 Setup Guide

1. Open the WorkspaceGPT sidebar in VSCode
2. Select your preferred AI provider from the settings menu
3. Configure your selected provider (API keys for cloud providers or connection settings for Ollama)
4. Confluence: Go to Settings > Confluence Integration, securely sign in with one click, and select workspaces to "Start Sync".
5. Azure DevOps (ADO): Go to Settings > Azure DevOps, provide your details, and sync your ADO context to chat with tickets and PRs.

🔁 Reset WorkspaceGPT

If you ever need to reset WorkspaceGPT to its default state, simply go to:

Settings > Reset VSCode State

🧑‍💻 Running the project locally

If you have source access, you can run the project locally:

pnpm install
pnpm run dev

Development Commands

• pnpm run dev - Start development mode
• pnpm run watch - Watch for file changes and rebuild
• pnpm run lint - Run ESLint
• pnpm run test - Run test suite

📦 Publishing

The extension is distributed through two registries:

• VS Code Marketplace (vsce) — used by Microsoft VS Code.
• Open VSX (ovsx) — used by VS Code forks such as Antigravity, Cursor, Windsurf, and VSCodium. The Microsoft Marketplace cannot be used by these forks, so the extension must be on Open VSX to be discoverable there.

Commands:

• pnpm run vscode:package — build and package a .vsix locally (e.g. for manual install).
• pnpm run vscode:publish-marketplace — publish the already-packaged .vsix to the VS Code Marketplace.
• pnpm run vscode:publish-pre-release-marketplace — same, marked as a pre-release.
• pnpm run vscode:publish-ovsx — publish the already-packaged .vsix to Open VSX (requires OVSX_TOKEN).
• pnpm run vscode:publish-pre-release-ovsx — same, marked as a pre-release.
• pnpm run vscode:publish-all — package once, publish the same artifact to both registries via the scripts above, then tag the release.
• pnpm run vscode:publish-pre-release-all — same, using the pre-release variants throughout.

If a full run fails partway (e.g. a registry outage), don't re-run -all — vsce publish will reject a version already live on the Marketplace. Instead, run just the step(s) that didn't complete, e.g. pnpm run vscode:publish-ovsx && pnpm create-tag.

Setup for Open VSX (one-time): create a publisher namespace matching Riteshkant at open-vsx.org, generate an access token, and export it before publishing:

export OVSX_TOKEN=<token>
pnpm run vscode:publish-all

Manual install (any fork): pnpm run vscode:package, then use the IDE's Install from VSIX action.

📄 License

This software is proprietary. See the LICENSE.md file for more details.

💬 Support

Have questions or issues?

1. Check the documentation
2. Open an issue on GitHub
3. Email us at contact@workspacegpt.in
4. Reach out to the maintainers

🙏 Acknowledgments

• Big thanks to the VSCode team for a powerful extension API
• And to all the contributors who help shape WorkspaceGPT

WorkspaceGPT – Talk to your code and your Confluence docs. Locally, privately, and intelligently.