Mindify Cortex for VS Code
An AI coding companion that reads, edits, and runs code right inside your editor.
Tutorial, Ask, Plan, and Agent — four focused modes backed by the Cortex platform, with an optional fully-local agent harness for power users.
Install · Sign in · Modes · Models · Configuration · Commands
Why Cortex?
- Sidebar-native. Lives in the VS Code Activity Bar — no context switch to a browser tab.
- Four modes, one prompt box. Tutorial to learn, Ask to read, Plan to research, Agent to edit and run.
- Workspace-aware. Attach the active selection, the open file, or a workspace map in one click.
- Multi-provider. Anthropic, OpenAI, and Google Gemini models behind a single picker.
- Private by default. Your code stays in your workspace until a tool call you can see sends it out.
- Optional local Agent. Drop in an Anthropic API key and Agent mode runs locally through the Pi agent harness — full workspace tools, approval prompts, no round-trip to the server.
Sign in
A single browser round-trip pairs the extension with your Cortex workspace and stores the session in VS Code's secret storage. The extension auto-recovers a stale token without prompting you again.
Your code stays in your workspace — never sent without a tool call you can see.
Modes
Cortex ships two tabs at the top — Chat and Agent — and the Agent tab has three submodes selected from the mode picker.
Tutorial (Chat tab)
A patient teacher. Cortex turns every prompt into a numbered, step-by-step walkthrough — what to do, the exact code, why it works, and a checkpoint to confirm. Great for onboarding to an unfamiliar codebase.
/ for slash commands (skills) · @ to mention files · ⌘K to start a new chat
- Quick-start prompts adapt to the file you have open
- Mermaid diagrams and syntax-highlighted code blocks render inline
Ask, Plan, Agent (Agent tab)
The Agent tab carries three submodes, each with its own guardrails:
| Submode |
What it does |
Can edit files? |
Can run commands? |
| Ask |
Workspace-aware Q&A, read-only |
– |
– |
| Plan |
Research and outline before any change |
– |
– |
| Agent |
Edit and run with tools (read_file, replace_in_file, write_file, list_files, run_command) |
yes |
yes |
Cortex Agent always names the tool it's about to use and explains why — and asks for approval on writes and shell commands. Approval behavior is configurable: ask, alwaysAllow, or readOnly.
Multi-provider model picker
Switch models without leaving the sidebar. The picker exposes Anthropic, OpenAI, and Google Gemini models — including Claude Opus 4.7, GPT-5.4, and Gemini 3.0 Pro — and remembers your choice per workspace.
Context attachments
The composer accepts more than text. Cortex tracks every attachment, shows how much of it fit in the prompt, and lets you toggle items on or off before sending.
- Use Selection — drop your highlighted code in as fenced context
- Use Current File — attach the file you're focused on
- Use Workspace — insert a repo map plus key files
- Upload files or paste images — multimodal context, attached straight to the message
- @ mentions — type
@ to find and attach any file in the workspace
- Skills — type
/ to invoke a workspace skill or slash command
Install
The latest packaged build lives in dist/. Install it from VS Code:
Command Palette → "Extensions: Install from VSIX..." → dist/mindify-cortex-vscode-0.7.11.vsix
Or from the terminal:
code --install-extension dist/mindify-cortex-vscode-0.7.11.vsix
The Cortex icon will appear in your Activity Bar.
Configuration
Configure via the Settings UI or settings.json:
{
"mindifyCortex.baseUrl": "https://cortex.mindifyai.dev",
"mindifyCortex.chatEndpoint": "/api/mobile/chat",
"mindifyCortex.agentEndpoint": "/api/mobile/chat",
"mindifyCortex.requestTimeoutMs": 240000,
"mindifyCortex.anthropicApiKey": "",
"mindifyCortex.agentModel": "claude-sonnet-4-6",
"mindifyCortex.permissionMode": "ask",
"mindifyCortex.allowFileWrites": true,
"mindifyCortex.allowCommandExecution": true,
"mindifyCortex.allowedTools": [
"read_file",
"list_files",
"replace_in_file",
"write_file",
"run_command"
]
}
| Setting |
What it does |
baseUrl |
Cortex backend URL (defaults to https://cortex.mindifyai.dev) |
chatEndpoint / agentEndpoint |
Override the request paths if you're self-hosting |
requestTimeoutMs |
Max time per request — bump it if you're using slow models |
anthropicApiKey |
When set, Agent mode runs locally through the Pi agent harness against your workspace |
agentModel |
Default model used by the local Pi agent harness (e.g. claude-sonnet-4-6) |
permissionMode |
ask (prompt before risky actions), alwaysAllow, or readOnly |
allowFileWrites |
Master switch for replace_in_file / write_file (and Pi equivalents) |
allowCommandExecution |
Master switch for run_command / Pi bash |
allowedTools |
Tool allowlist — accepts both remote and Pi tool names |
Advanced users can still set mindifyCortex.authToken or mindifyCortex.apiKey manually for self-hosted or service-account setups, but browser sign-in is the default flow.
Commands
| Command |
What it does |
Mindify Cortex: Open Chat |
Focus the Cortex sidebar |
Mindify Cortex: Clear Conversation |
Reset the current thread |
Keyboard tips inside the composer:
Enter to send · Shift+Enter for a newline
/ for commands · @ to mention files · ⌘K for a new chat
Threads & history
Up to 50 threads per mode are kept locally and synced with the Cortex backend when you're signed in. Switch threads from the sidebar header, or hit ⌘K to start fresh — the previous thread is preserved.
Local development
cd vscode-extension
npm install
npm run compile
Then press F5 in VS Code to launch an Extension Development Host.
Packaging
npm i -g @vscode/vsce
cd vscode-extension
vsce package