kapelame/deepseek-harness-leetcode
DeepSeek Harness LeetCode brings algorithm practice inside DSH: all of LeetCode Hot 100 plus eight classics with summaries, progressive hints and explained solutions, 16 lesson topics, a sandboxed Docker judge with hidden boundary and random cases, an AI tutor with spaced repetition, and the ability to add problems from a plain description.
DeepSeek Harness LeetCode brings algorithm practice inside DSH. It covers all of LeetCode Hot 100 plus eight more classics, each with an original summary, three progressive hints and an explained solution while the statements stay on LeetCode and every problem links to its official page. 16 lesson topics, from hashing to dynamic programming, precede the problems with worked examples that can be traced step by step. A real judge runs code on your machine in Docker with no network and hidden boundary, random and large cases that catch wrong and slow solutions, including design classes, in-place edits and linked-list/tree node problems. It also adds an AI tutor chat, spaced-repetition reviews with fresh validated variants, progress by concept, optional daily reminder email, and the ability to add new problems by describing them in plain language - an agent finds them on LeetCode, writes the tests and adds them only if they pass validation.
Install
dsh plugin --profile web add github:kapelame/deepseek-harness-leetcodeCopied verbatim from the README's Web install block (the Desktop route installs from GitHub via the Plugins page); the README's Quick start shows the same command followed by dsh web.
Compatibility
Runs on DeepSeek Harness Desktop and Web and needs Docker installed with the runner images pulled once (docker pull python:3.13-alpine node:24-alpine); code is judged in Docker with no network. Explanations default to Chinese and can be switched to English in Learn -> Settings.
Details
- Repo: kapelame/deepseek-harness-leetcode
- Category: Learning & Research
- Stars: 1
- Version: GitHub repo kapelame/deepseek-harness-leetcode (1★, MIT); installed from GitHub (no npm package documented). Needs DSH 0.2.0-rc.2 or newer, below 0.3 (tested on 0.2.0-rc.2 and 0.2.1-alpha.3). A default model is optional - it powers the tutor, AI feedback and Add problems, while running, judging and written hints work without one.
Alternatives
1692775560/dsh-Mimir-Academic-research · Astervolans/dsh-literature-search · beibingyangliuying/dsh-autoresearch