Deleetify

Makes local LeetCode setup less painful.

A CLI tool that fetches any LeetCode problem and uses an AI agent to generate a ready-to-run boilerplate solution file — so you can jump straight into solving, not scaffolding.

Features

• Fetch any LeetCode problem by id
• AI-generated boilerplate via any ACP-compatible agent (e.g., opencode, claude-code)
• Supports Python and JavaScript starter code
• Configurable AI provider via TOML

Installation

Note: If any problem encountered, try installing with python 3.13

pip install deleetify

Or with uv:

uv tool install deleetify

Usage

# Basic usage — generates Python boilerplate
deleetify "208"

# Specify language
deleetify "1" --lang javascript

# Custom config path
deleetify "15" --config ./my-agent.toml

Configuration

Deleetify uses a deleetify.toml to configure the AI provider. By default it looks for the file in the current directory.

[provider.opencode]
command = "opencode"
args = ["acp"]

If you have multiple providers, set a default:

[default]
provider = "opencode"

[provider.opencode]
command = "opencode"
args = ["acp"]

[provider.gemini]
command = "gemini"
args = ["--acp"]
# envs = {SOME_ENV = "value"}

If you want to modify leetcode api (for development it is recommended):

[config]
leetcode_api = "https://alfa-leetcode-api.onrender.com/" # It is the default

[provider.opencode]
command = "opencode"
args = ["acp"]

How it works

1. You pass a LeetCode problem id (e.g., 208)
2. Deleetify parses the name and fetches the problem from the LeetCode API
3. It scrapes the description, examples, and starter code from the HTML response
4. It spawns an AI agent subprocess over the Agent Communication Protocol (ACP)
5. The agent receives a prompt with the problem details and generates boilerplate code with built-in test cases

Supported languages

Requirements

• Python 3.13+
• An ACP-compatible agent (e.g., opencode)

License

MIT