VS Code Extension

The Sagewai VS Code extension accelerates agent development with directive syntax highlighting, scaffold commands, and code snippets. Zero configuration required.

Installation

From VSIX (Current)

cd vscode/
npm install
npm run compile
npx @vscode/vsce package

Then in VS Code: Command Palette → "Extensions: Install from VSIX..." → select the generated .vsix file.

From Source (Development)

Open the vscode/ directory in VS Code
Press F5 to launch the Extension Development Host
The extension auto-activates for Python and Markdown files

VS Code Marketplace (Coming Soon)

ext install sagewai.sagewai

Features

Directive Syntax Highlighting

The extension injects syntax highlighting for all Sagewai directive types in Python and Markdown files. Directives are visually distinguished from regular code, making it easy to spot retrieval, delegation, and configuration at a glance.

Supported directives:

Directive	Purpose	Example
`@context()`	Retrieve documents from Context Engine	`@context('quarterly earnings', scope='project', tags='finance')`
`@memory()`	Search stored facts	`@memory('customer preferences')`
`@agent:name()`	Delegate to another agent	`@agent:researcher('Find latest pricing data')`
`@wf:name()`	Invoke a saved workflow	`@wf:approval_pipeline('Review this contract')`
`/tool.name()`	Call a tool inline	`/tool.web_search('Sagewai documentation')`
`#model:name`	Override the model	`#model:gpt-4o`
`#budget:amount`	Set a budget limit	`#budget:1.00`
`@datetime`, `@date`, `@time`	Dynamic parameters	Resolved at prompt-processing time
`@user`, `@project`	Context parameters	Current user and project
`{{ expression }}`	Template expressions	`{{ context.search('query') }}`

Scaffold Commands

Access from the Command Palette (Cmd+Shift+P / Ctrl+Shift+P):

Sagewai: New Agent

Generates a complete agent file with:

Imports (UniversalAgent, tool)
An example @tool decorated function
Agent configuration (name, model, system_prompt, tools)
Async usage example

from sagewai import UniversalAgent, tool

@tool
async def search_web(query: str) -> str:
    """Search the web for information."""
    # TODO: implement
    return f"Results for: {query}"

agent = UniversalAgent(
    name="my-agent",
    model="gpt-4o",
    system_prompt="You are a helpful research assistant.",
    tools=[search_web],
)

# Usage: response = await agent.chat("Find the latest AI news")

Sagewai: New Workflow

Generates a multi-agent sequential pipeline:

from sagewai import UniversalAgent, SequentialAgent

researcher = UniversalAgent(
    name="researcher",
    model="gpt-4o",
    system_prompt="You research topics thoroughly.",
)

writer = UniversalAgent(
    name="writer",
    model="gpt-4o",
    system_prompt="You write clear, engaging content.",
)

pipeline = SequentialAgent(
    name="research-pipeline",
    agents=[researcher, writer],
)

# Usage: result = await pipeline.chat("Write an article about quantum computing")

Sagewai: Add Tool

Inserts a @tool decorated function at your cursor position with interactive tabstops — Tab through the function name, parameters, and docstring.

Code Snippets

Type a prefix and press Tab to expand:

Prefix	Expands To	Use Case
`swagent`	Full agent with tool and config	Quick agent setup
`swtool`	`@tool` decorated function	Add a single tool
`swworkflow`	Sequential dual-agent pipeline	Multi-stage workflows
`swctx`	`@context('query', scope='project', tags='...')`	Context retrieval directive
`swmem`	`@memory('query')`	Memory search directive
`swag`	`@agent:name('task')`	Agent delegation directive

How It Improves Your Workflow

Eliminates boilerplate — Scaffold a complete agent in 2 seconds instead of 30 seconds of typing. Every generated file follows SDK conventions (async patterns, proper imports, tool decorator).

Visual feedback — Catch directive syntax errors before running your code. Highlighted directives stand out from regular Python strings, making prompt engineering more visual.

Consistent patterns — Generated code always follows Sagewai conventions: async functions, proper imports, UniversalAgent configuration, tool decorator patterns.

Interactive tabstops — When using scaffold commands or snippets, Tab through placeholders to fill in names, prompts, and parameters without touching boilerplate.

Works alongside AI assistants — The extension complements Copilot, Cursor, and Claude Code. Syntax highlighting helps AI assistants understand your directives, while snippets provide the scaffolding that AI fills in.

Configuration

Zero configuration needed. The extension activates automatically when you open any Python or Markdown file. All features work out of the box.

Requirements:

VS Code 1.85.0 or later
No runtime dependencies

Technical Details

Activation events: onLanguage:python, onLanguage:markdown
Grammar injection: TextMate grammar patterns injected into Python and Markdown
Bundle size: Minimal — no runtime dependencies, compiles to a single JS file