https://github.com/kuutsav/leetcode-compensation
Near real-time leetcode compensation insights
https://github.com/kuutsav/leetcode-compensation
indian leetcode leetcode-compensation llms python3
Last synced: 27 days ago
JSON representation
Near real-time leetcode compensation insights
- Host: GitHub
- URL: https://github.com/kuutsav/leetcode-compensation
- Owner: kuutsav
- License: mit
- Created: 2021-06-18T09:33:07.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2026-02-13T05:10:22.000Z (about 1 month ago)
- Last Synced: 2026-02-13T11:57:22.867Z (about 1 month ago)
- Topics: indian, leetcode, leetcode-compensation, llms, python3
- Language: Python
- Homepage: https://kuutsav.github.io/leetcode-compensation/
- Size: 27.9 MB
- Stars: 360
- Watchers: 11
- Forks: 62
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## Leetcode Compensation
[https://kuutsav.github.io/leetcode-compensation/](https://kuutsav.github.io/leetcode-compensation/)
A tool that helps you find **Software Engineer Salary in India** by:
- Fetching compensation data from Leetcode forums
- Updating regularly through GitHub action PRs
- Using LLMs for parsing and sanitizing structured data from posts, followed by aggregation
## Getting Started
Install uv from [Standalone Installers](https://docs.astral.sh/uv/getting-started/installation/) or from [PyPI](https://pypi.org/project/uv/):
```bash
uv sync # Install all dependencies from pyproject.toml
```
## Updating Data
The project uses **LM Studio** by default with the `openai/gpt-oss-20b` model for:
- Parsing salaries, years of experience (YOE), and other compensation details from posts
- Normalizing fields like companies, roles, and locations into structured format
Make sure you have:
- [LM Studio](https://lmstudio.ai/) installed and running
- The `openai/gpt-oss-20b` model downloaded and loaded
- Server running on `http://localhost:1234`
Alternatively, you can use GitHub Models by setting `Provider.GITHUB_MODELS` and the `GITHUB_TOKEN` environment variable.
To sync and fetch new compensation data:
```bash
uv run leetcomp-sync
```
## LLM Assistance
I've written all the data parsing logic in python by hand. Most of the prompts have been generated with the assistance of claude-sonnet-4.5 and pretty much all of the html file has been generated by claude-opus-4.5.