Home/Python
Python · Google · NumPy · Sphinx · Epytext

Python docstrings with AI
Auto-generated.

One command writes Google, NumPy, or Sphinx docstrings for every undocumented function in your Python project — with drift detection to catch stale docs before they merge.

Start Freepip install wright
4 styles
Doc styles supported
0
Config required
Free
No credit card

See it in action

Before and after — Google style

Wright AI reads the function body, its callers, and its callees — generating documentation that reflects real intent, not just syntax.

BEFORE · undocumented
def calculate_discount(price, user_tier, coupon_code=None):
    if user_tier == "premium":
        discount = 0.20
    elif coupon_code and coupon_code in VALID_COUPONS:
        discount = VALID_COUPONS[coupon_code]
    else:
        discount = 0.0
    return price * (1 - discount)
AFTER · wright generate
def calculate_discount(price, user_tier, coupon_code=None):
    """Calculate the final price after applying tier and coupon discounts.

    Args:
        price (float): The original item price before discounts.
        user_tier (str): User membership tier. "premium" receives
            an automatic 20% discount.
        coupon_code (str, optional): Promotional code. Defaults to None.

    Returns:
        float: The discounted price.

    Example:
        >>> calculate_discount(100.0, "premium")
        80.0
    """

How it works

More than a docstring generator.

WrightAI generates, verifies and maintains documentation — so docs stay accurate as your Python codebase evolves.

Call-graph context
Wright builds a dependency graph before generating. It reads what calls your function and what it calls — so docs describe purpose, not just mechanics.
Coverage tracking
Know the exact % of documented functions across every file. Set a minimum threshold and enforce it in CI so coverage never regresses.
Drift detection
When a function signature changes, Wright flags the stale docstring — as a VS Code gutter warning and a CI failure. No more silent documentation lies.
MCP for AI tools
Exposes your indexed docs to Claude Code, Cursor, and Copilot via MCP so every AI response is grounded in live, verified codebase knowledge.

Comparison

How Wright differs from alternatives.

Most tools for Python documentation either render what exists or suggest one comment at a time. Wright does neither.

Writing manually
gap

Takes 5–10 min per function. Gets skipped under deadline pressure. Goes stale silently.

GitHub Copilot
gap

Suggests one function at a time on demand. No batch generation, no coverage tracking, no drift detection.

Sphinx autodoc
gap

Generates docs from existing docstrings — it doesn't write them. You still need to author every string.

Wright AI
solves this

Batch-generates Google/NumPy/Sphinx/Epytext documentation across your entire Python codebase. Tracks coverage. Detects drift on every commit. Feeds live docs to AI tools via MCP. Free to start.

Documentation Intelligence Platform

Start documenting your Python codebase.

Free VS Code extension · CLI · GitHub Action · MCP server.
No credit card required.

Start FreeRead the Docs