New: WorkspaceGPT Desktop for macOS and Windows — no editor required

The coding agent that knows your whole org

Other coding agents start from your repo and a prompt. WorkspaceGPT starts from the ticket and the design doc — it reads your Confluence, Jira and Azure DevOps mid-task, then edits your code and runs your tests. Every change is a diff you approve first, and your org's knowledge and its search index never leave your machine.

Get the desktop appHow privacy works →
WorkspaceGPT
The WorkspaceGPT sidebar answering “Why is the payment retry capped at 3?” — it searched Confluence and the codebase, then cited the Retry & Backoff Policy page, src/payments/retryPolicy.ts and Azure DevOps work item #12359.

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 docs and tickets, 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

A full agent that reads, edits and verifies — with the docs and tickets that explain why already in reach.

Agentic coding

The agent searches and reads your code, makes multi-file edits, then runs your linter, type-checker and tests to verify its own work before handing it back.

Your org's knowledge, mid-task

Confluence pages, Jira issues and Azure DevOps work items, synced and searchable. The agent pulls them mid-task, so a run is grounded in the design page and the ticket that asked for it — not just the file.

In your editor, or on its own

Install it in VS Code, Cursor or Antigravity — or run WorkspaceGPT Desktop, the same agent as an app for macOS and Windows. Open a folder and go.

Review before it writes

Every file change arrives as a diff you approve or reject. A checkpoint is taken before the first write, so one click reverts the whole turn.

Codebase understanding

ripgrep search plus symbol, definition and reference lookup through a real language server — your editor's, or the one bundled with Desktop.

Your work, on open

The sidebar lists the ADO items assigned to you with their state and sprint — start a run straight from a ticket.

Web search mid-task

Lets the agent look up what your code and docs can't tell it: a new library, an unfamiliar API, current release notes.

@-mentions

Pull a specific file or folder into the conversation instead of hoping retrieval finds it.

Release automation

Config-sync and hotfix pipelines with a plan → approve → apply flow, so work doesn't stop at “PR opened”.

MCP server

Ships an MCP server that exposes your Confluence, Jira and Azure DevOps search to Claude Desktop, Cursor and other MCP clients.

Runs offline

In Local mode with Ollama there are no remote APIs at all — the whole loop works on a plane.

Chat where you want it

Run it in the sidebar or open it as a full editor tab, with several sessions going at once.

From an assigned ticket to a verified answer

Open the sidebar and your work is already there. Pick a ticket and the agent takes it from the docs to the code to the test run.

WorkspaceGPT open as a full editor tab, working bug #248721 “Authentication token not refreshing after session”. Five completed steps — analyse, plan, implement, run tests, verify — show the files it modified, unit 12/12, integration 5/5 and e2e 3/3 passing, and the task completed in 1 minute 5 seconds.
One bug, start to finish. It plans the fix, edits the files, runs the unit, integration and end-to-end suites, then re-checks the original failing scenario — and hands you a diff.
The WorkspaceGPT sidebar on open: a “Your work” list of assigned Azure DevOps items with their type, state and sprint, recent chats below it, and a suggested “Fix #1829411” action.
Your work, already loaded. The items assigned to you, with state and sprint — no hunting for a ticket ID to paste in.
An agent run grounded in user story #4598: after 63 steps it reports “No change needed — the caching logic for user profiles is already implemented in the service layer”, cites the files and line ranges it read, and shows three cache tests passing.
It will tell you there is nothing to do. Sixty-three steps, every file it read cited, and the tests run to prove it — rather than inventing a change to look busy.

Run it where you work

The same agent, the same knowledge and the same privacy guarantees — in your editor, or as an app of its own.

New · macOS · Windows

WorkspaceGPT Desktop

No editor needed. Open a project folder and the agent reads, edits and tests it, with your Confluence, Jira and Azure DevOps knowledge in reach. Paste one line:

macOS · Terminal

curl -fsSL https://github.com/ritesh-kant/workspaceGPT/releases/download/desktop-latest/install.sh | sh

Windows · PowerShell

irm https://github.com/ritesh-kant/workspaceGPT/releases/download/desktop-latest/install.ps1 | iex
  • Apple Silicon and Intel Macs (macOS 12+), and Windows x64
  • Updates itself — every update is signed and verified before it installs
  • Secrets in the macOS Keychain or Windows Credential Manager; indexes stay on your machine
Prefer a DMG or setup.exe? Download it from GitHub

The app isn't notarized or code-signed yet. The one-line installers need nothing extra. A DMG needs one “Open Anyway” in System Settings › Privacy & Security; a browser-downloaded setup.exe needs “More info › Run anyway”. Linux is on the way.

VS Code · Cursor · Antigravity

Editor extension

Lives in your editor's sidebar or a full editor tab, and uses your editor's own language server for symbol lookups. From the VS Code Marketplace, or Open VSX for Cursor and Antigravity.

ext install Riteshkant.workspacegpt-extension

Ready in minutes

1

Installation

Add the extension to VS Code, Cursor or Antigravity, or install WorkspaceGPT Desktop on a Mac.

ext install Riteshkant.workspacegpt-extension
2

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 / Claude / Gemini / Groq / OpenRouter key — or any OpenAI-compatible endpoint.
  • 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.

3

Connect your org's knowledge

Confluence and Jira

Go to Settings > Knowledge > Confluence or Jira and click Connect to sign in with your Atlassian account. Pick a space or project and hit Sync.

Azure DevOps

Go to Settings > Knowledge > Azure DevOps, enter your organization and a Personal Access Token to sync work items and the tickets behind Your work.