Chat with your codebase, plan changes, edit files, run tests, and create projects from inside VS Code. Workspai combines an AI coding assistant with workspace intelligence: a shared view of your projects, dependencies, and supporting evidence.
Ask → inspect → change → test → verify
- Install Workspai.
- Open an existing repository or start a new workspace in VS Code.
- Open the Workspai sidebar and start a chat or create a project.
- Choose an available model or configure your provider, then describe the task.
Start with an existing repository; Workspai registration is optional. Try:
- "Explain how authentication works in this project."
- "Add a regression test for this bug and run the relevant checks."
- "Create a separate workspace with a Next.js frontend and a NestJS API."
On first use, the extension downloads and integrity-checks its pinned Workspai CLI runtime, then reuses the cached copy offline. A separate global CLI install is not required for extension-owned operations.
Work on existing projects without mandatory adoption, preview attached images, and review each task's file changes above the composer. A compact chat picker and activity grouped by response keep conversations focused. Read the release notes.
| Mode | Best for |
|---|---|
| Ask | Understanding code, architecture, diagnostics, and workspace state. |
| Plan | Investigating a task and preparing a grounded, read-only plan. |
| Agent | Editing code, running scoped checks, and verifying the result. |
| Goal | Pursuing a defined outcome with explicit checks and progress. |
Ask and Plan stay read-only. Agent and Goal can make scoped changes and report the checks performed, their results, and any remaining verification.
Workspai connects source code with projects, dependencies, contracts, diagnostics, and documentation. The Assistant can use this context alongside source search, project commands, web research, and enabled VS Code/MCP tools.
Describe the workspace or project you want. Workspai prepares a clear plan for review before it creates files or runs setup commands.
Use one conversational loop to inspect evidence, edit source, run project commands, review changed files, and verify the outcome. When an operation needs permission, the Assistant shows an approval card in the conversation. You can run it once, allow the exact action for the session or project when supported, or decline it.
An ordinary Agent task does not need an incident card or Workspai registration. Select an existing project and describe the task. Adoption in place or import of a copy into Workspai requires approval. You can continue ordinary project work without registering it.
Review file changes and exact diffs above the composer, then Keep changes or Restore the task checkpoint. Follow activity for each response, inspect command output, and stop running work. Attached images have thumbnails and full previews.
Explore how projects, modules, files, APIs, and dependencies connect. Select an entity to inspect its relationships and supporting evidence.
Follow active commands, completed stages, failures, check results, and model usage. Operations Floor brings workspace activity, Graph context, and supporting evidence into one view.
Open the generated Model, Graph, agent context, Skills, reports, and other workspace evidence without searching through internal directories.
- Read-only investigation can run without unnecessary prompts.
- Source changes are scoped, recorded, and reversible where supported.
- Sensitive or invasive actions require an explicit, exact approval.
- Check results and unfinished verification are reported explicitly.
- Agent changes can carry their intent, observed effects, and verification as one inspectable record.
Use models available through VS Code, including those exposed by GitHub Copilot, or configure a supported API provider or local model. Codex and Grok model availability depends on your provider, account access, and configuration.
VS Code Models · OpenAI · Claude · Gemini · Kimi · DeepSeek ·
OpenRouter · Groq · Mistral · xAI (Grok) · Ollama · Custom
Provider credentials are stored in VS Code Secret Storage. Tool and image support depends on the selected model and enabled providers.
- Getting started
- CLI Repair Engine integration
- Release notes
- Workspai CLI
- Contributing
- Issues and feature requests
MIT © Chistiq

