Krnl Code - VS Code Extension

A lightweight agentic coding assistant that brings the power of autonomous AI coding directly to your editor. Plan, edit, and run code with approvals using your preferred AI provider.

Settings

Features

Universal Model Support: Works with Krnl/Krnl, OpenAI, OpenRouter, Anthropic, Ollama, or any OpenAI-compatible/self-hosted model
Autonomous Coding: The agent plans, reads, edits, runs commands, and verifies results iteratively until your task is complete
Approval Workflow: Human approval required for potentially dangerous operations - you stay in control
Plan Mode: Research and propose changes before execution - perfect for complex refactors
Multi-Model Routing: Assign different models to different phases (plan/execute/subagent/verify) for optimal cost-performance
Security First: Built-in security auditing, dependency scanning, and approval workflows
Session Persistence: Remember conversations per workspace across reloads
Project Memory: Create AGENTS.md files to provide project-specific context to the agent
CLI Integration: Full command-line interface for headless operation and CI/CD pipelines

Installation

VS Code Marketplace

Install "Krnl Code" directly from the VS Code Marketplace

Open VSX (for Cursor, VSCodium, Windsurf)

Install from Open VSX

Manual Installation

Download the extension directly: krnl-code.vsix

Then install from the command line:

code --install-extension krnl-code.vsix

Or build from source:

# Install using vsce
npm install -g @vscode/vsce
cd extension
vsce package
code --install-extension krnl-code-*.vsix

Quick Start

Install the Extension - Search for "Krnl Code" in the VS Code Extensions panel and install
Open the Chat Panel - Click the robot icon in the activity bar or run Krnl Code: Open Chat
Configure Your Provider - Click the key icon to set your API key and select your provider
Start Coding - Type your task in the chat and watch the agent work!

Configuration

Setting API Key

Open the Krnl Code chat panel
Click the key icon (Set API Key / Provider) or run Krnl Code: Set API Key / Provider
Select your provider (openai, anthropic, gemini, groq, ollama, etc.)
Paste your API key when prompted
Your key is stored securely in ~/.krnl-code

Settings

Provider Selection

OpenAI: Supports GPT-4, GPT-3.5, and other OpenAI models
Anthropic: Native Claude support with enhanced capabilities
Google Gemini: Direct integration with Google's models
OpenRouter: Access to 200+ models through a single API
Groq: Ultra-fast inference with Llama and Mixtral models
Ollama: Run local models like Llama 3, Mistral, etc.
Custom: Any OpenAI-compatible endpoint

Extension Settings

Configure these in VS Code Settings (Ctrl+,) under Krnl Code:

Model: Override the model ID for the active provider (empty = provider default)
Python Path: Python 3.9+ executable for the managed backend (empty = auto-detect)
Backend Version: Pin the krnl-code backend version (empty = latest)
Server URL: Connect to a self-hosted backend (advanced)
Token: Bearer token for remote/self-hosted backend
Persist History: Remember conversation per workspace across reloads (default: true)
Effort: Reasoning effort for thinking-capable models (low/medium/high)
Auto Diagnostics: Offer to fix new error diagnostics after tasks (default: true)

Commands

Chat & Task Management

Command	Description
`Krnl Code: Open Chat`	Open the main chat interface
`Krnl Code: Stop Current Task`	Stop the currently running task
`Krnl Code: Undo Last Task's Changes`	Revert file changes from the last task

Configuration

Command	Description
`Krnl Code: Set API Key / Provider`	Configure your API key and provider
`Krnl Code: Select Provider`	Switch between AI providers
`Krnl Code: Set Model`	Change the model for the active provider
`Krnl Code: Select Workspace Folder`	Choose the working directory

Modes & Controls

Command	Description
`Krnl Code: Toggle Auto-Approve`	Enable/disable automatic approval for edits
`Krnl Code: Toggle Plan Mode`	Switch between plan and execute modes
`Krnl Code: Toggle Dangerous Mode`	Disable all approvals (use with caution!)

Project & Memory

Command	Description
`Krnl Code: Create Project Memory`	Create AGENTS.md for project-specific context
`Krnl Code: Onboard Project`	Scaffold .krnl/ wrapper with memory and skills

Code Quality & Security

Command	Description
`Krnl Code: Fix Diagnostics`	Automatically fix error diagnostics in changed files
`Krnl Code: Review Changes`	Review uncommitted git changes for bugs and improvements

Backend Management

Command	Description
`Krnl Code: Restart Backend`	Restart the Python backend server
`Krnl Code: Attach Image`	Attach an image to the current conversation

Account

Command	Description
`Krnl Code: Login`	Authenticate with your Krnl Code account
`Krnl Code: Check Authentication Status`	View your current authentication status
`Krnl Code: Logout`	Sign out of your account

In-Chat Slash Commands

While in the chat interface, you can use these commands:

Setup & Configuration

/provider <name> - Switch the active provider
/key - Set the API key for the active provider
/model <id> - Set the model ID
/baseurl <url> - Set custom base URL
/config - Show current configuration
/providers - List all provider profiles
/models - Show multi-model routing table
/effort <low|medium|high> - Set reasoning effort

Modes

/plan - Enable plan mode (research first, then execute)
/execute - Enable execute mode (default)

Code Work

/review - Review uncommitted git changes
/security - Full security audit of the codebase
/scan - Fast secret + dependency vulnerability scan
/secfix - Autonomous security remediation
/test [target] - Write and run tests
/testall - Build comprehensive test suite
/ship [what] - End-to-end: plan → build → test → deploy
/deploy [target] - Deploy to a live URL
/monitor - Show monitoring status
/heal [url] - Self-heal deployment

Project & Memory

/init - Create AGENTS.md project memory
/onboard - Scaffold .krnl/ wrapper
/skills - List available skills
/search <text> - Search past sessions

Safety & Diagnostics

/audit - Show tamper-evident action log
/doctor - Run environment self-check
/yes - Toggle auto-approve
/dangerous - Toggle dangerous mode

Session Control

/usage - Show token usage and costs
/compact - Summarize conversation to free context
/undo - Revert last task's changes
/reset - Clear conversation context
/help - Show help
/exit - Quit session

CLI Installation

For headless operation or CI/CD integration, install the CLI using the one-liner:

Windows (PowerShell):

irm https://krnl.ai/install.ps1 | iex

macOS / Linux:

curl -fsSL https://krnl.ai/install.sh | sh

Or download the standalone binary:

Download the pre-built executable for your platform from Vercel Blob storage:

Platform	Download
Windows x64	krnl-code-windows-x64.exe
macOS (Apple Silicon)	krnl-code-macos-arm64
Linux x64	krnl-code-linux-x64

Note: macOS Intel (x64) is not currently supported. Please use an Apple Silicon (ARM64) Mac or build from source.

# Linux / macOS
chmod +x krnl-code-*
./krnl-code-* --help

# Start interactive session
./krnl-code-*

# Run single task
./krnl-code-* run "Fix the login bug"

# Auto-approve mode
./krnl-code-* run "Add tests" --yes

# Windows (double-click or run in terminal)
krnl-code-windows-x64.exe --help

# Start interactive session
krnl-code-windows-x64.exe

# Run single task
krnl-code-windows-x64.exe run "Fix the login bug"

# Auto-approve mode
krnl-code-windows-x64.exe run "Add tests" --yes

CLI Commands

Command	Description
`krnl-code`	Start interactive session
`krnl-code run "<task>"`	Run single task and exit
`krnl-code serve`	Run HTTP/WebSocket server
`krnl-code providers`	List configured providers
`krnl-code models`	Show multi-model routing table
`krnl-code init`	Scaffold config.yaml and .env
`krnl-code update`	Update to latest version
`krnl-code onboard`	Scaffold .krnl/ wrapper
`krnl-code security`	Run security audit
`krnl-code scan`	Fast risk scan
`krnl-code secfix`	Security remediation loop
`krnl-code test`	Write and run tests
`krnl-code ship "<what>"`	End-to-end deployment
`krnl-code deploy`	Deploy to live URL
`krnl-code monitor`	Show monitoring status
`krnl-code heal`	Self-heal deployment
`krnl-code doctor`	Environment self-check
`krnl-code audit`	Show action log
`krnl-code init-ci`	Create GitHub Actions workflow
`krnl-code plugin`	Manage plugins/skills
`krnl-code sessions`	List saved sessions
`krnl-code team`	List multi-agent teams
`krnl-code schedule`	Cron-driven scheduled agents

How It Works

Task Input: You describe what you want to accomplish in natural language
Planning: The agent analyzes your request and creates a step-by-step plan
Execution: The agent uses tools to read files, edit code, run commands, and verify results
Approval: For potentially dangerous operations, the agent asks for your approval
Iteration: The agent continues until the task is complete or you stop it
Learning: The agent remembers context and improves with each interaction

Security & Privacy

Local Execution: All file operations happen on your machine
Approval Required: Dangerous operations require explicit approval
Audit Trail: All actions are logged in .krnl/audit/
Secure Storage: API keys stored securely in ~/.krnl-code
Sandbox: Tools run with appropriate permissions and restrictions
No Code Sending: Your code is only sent to the AI provider you choose

Requirements

VS Code: Version 1.85.0 or higher
Python: 3.9 or higher (auto-managed by extension)
API Key: For your chosen AI provider

Troubleshooting

Backend won't start

Ensure Python 3.9+ is installed
Check krnlAgent.pythonPath setting if using custom Python
Run Krnl Code: Restart Backend

API key issues

Verify your key is correct for the selected provider
Check provider status pages for outages
Try /config to view current configuration

Context issues

Use /compact to summarize long conversations
Enable project memory with /init or /onboard
Adjust model for larger context windows

Support

For issues and questions, please contact us at https://krnl-code.vercel.app/support