💾

Your data stays on your machine

Indexing and embeddings run on-device, and the vector index is written to local files. We never upload your documents or your code.

🗑️

Zero data retention

We store no prompts, no answers, no documents — not even in logs. In Remote mode your question is processed in memory and discarded.

🙈

Never used for training

Nothing you ask is used to train a model, sold, or shared. Anonymous feature-usage counts are all we measure — never your content.

Read the full privacy policy — it lists every byte we hold.

Two modes, one guarantee

The mode changes exactly one thing: where the answer is generated. Your documents, your code, and the search index built from them stay local either way.

🔐Local · Free

Everything runs locally

Your model, your hardware. With Ollama, none of your content leaves your computer — no account, no cloud round-trip. Prefer a bigger model? Plug in your own provider key and you still decide exactly where your data goes.

✓ Chat model on your machine via Ollama — or your own API key
✓ Embeddings generated on-device
✓ Vector index in local files
✓ No account — runs offline with a local model

⚡Remote · Preview

We run the infrastructure

We host the inference and choose the model, so there is nothing to configure and no model key to buy. Your data still stays local: only your question and the snippets retrieved for it reach our endpoint — and we keep none of it.

✓ Managed model — no provider keys, no setup
✓ Embeddings still generated on-device
✓ Vector index still in local files
✓ Sign in with GitHub; every request re-verified
✓ Zero retention — nothing stored, nothing logged

Remote mode is in preview. It is rolling out now and may change while we tune capacity and models. Local mode is generally available and is unaffected. Inference in Remote mode is performed by an upstream model provider under its own policy — see the privacy policy for exactly what travels where.

Capabilities designed for builders

Everything you need to navigate, understand, and build within your existing codebase seamlessly.

🤖

AI-Powered Q&A

Get context-aware answers from your local workspace using blazing fast Retrieval-Augmented Generation (RAG).

📄

Confluence One-Click

Seamlessly connect to your Confluence space and instantly start chatting with your documentation alongside your code.

🔷

Azure DevOps (ADO)

Deep integration with ADO to fetch work items, user stories, and pull requests directly into your AI context.

💬

Interactive Editor Chat

Ask questions directly in the IDE to receive intelligent, project-specific code solutions. Stop switching context.

Ready in minutes

Installation

WorkspaceGPT is available directly through the marketplace. Install it for VS Code, Cursor, or Antigravity.

ext install Riteshkant.workspacegpt-extension

Pick your mode

Open Settings > Mode. Either way, indexing stays on your machine.

Local — bring your own model. Ollama for fully offline (default llama3.2:1b), or your own OpenAI / Gemini / Groq / OpenRouter key.
Remote (preview) — sign in with GitHub and we handle the model. No keys, nothing to configure.

No re-index when you switch — the mode only moves inference, never your index.

Connect Contexts

Confluence Start

Go to Settings > Confluence. Click Sign in for one-click auth, and hit Sync.

ADO Synchronization

Go to Settings > ADO Integration. Enter PAT to sync pull requests, tickets, and work items.