- Stanford, CA
- http://keawang.github.io
Highlights
- Pro
Stars
- All languages
- Assembly
- C
- C#
- C++
- CMake
- CSS
- Clojure
- Cuda
- Cython
- Dart
- Dockerfile
- Elixir
- F#
- Fennel
- Fluent
- Go
- HTML
- Haskell
- Java
- JavaScript
- Jinja
- Julia
- Jupyter Notebook
- Kotlin
- Lean
- LiveScript
- Lua
- MATLAB
- MDX
- MLIR
- Markdown
- Metal
- Nim
- OCaml
- Objective-C
- PDDL
- PHP
- PostScript
- Python
- R
- Ruby
- Rust
- SAS
- SCSS
- Scala
- Shell
- Svelte
- Swift
- SystemVerilog
- TeX
- TypeScript
- Vala
- Vim Script
- Vue
- Zig
Create executable documents that demonstrate an agent's work
Slack for AI employees that build and maintain their own wiki. Get Claudes, Codexes, OpenClaws and local LLMs to collaborate and do your work autonomously while never losing context.
Hugging Face's take home challenge for post-training internships, now open for you to try!
Reverse of OpenAI Privacy Filter: same 1.5B model, returns PII as structured spans instead of masking.
Open-source Polymarket terminal — live book, trader leaderboard, self-custodial trading. No fees, no relayer, no builder credentials.
An extension of Nautilus Trader with custom Polymarket and Kalshi adapters for backtesting
Real-time Polymarket prediction market visualization dashboard with an interactive world map.
news-please - an integrated web crawler and information extractor for news that just works
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
FlashKDA: high-performance Kimi Delta Attention kernels
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
Use Claude Code with your ChatGPT or Kimi subscription via a local Anthropic-compatible proxy
Data and tools for generating and inspecting OLMo pre-training data.
Tool to build & run portable, lightweight, self-contained virtual machines.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
A comprehensive dataset of 1.1 billion trading records from Polymarket, processed into multiple analysis-ready formats. Features cleaned data, unified token perspectives, and user-level transformat…
Dissecting the Duck's Innards — A DuckDB-based course on the Design and Implementation of Database System Internals
Xterm LaTeX renderer for AI workflows
Scrape Google Trends data using Python or the Bright Data API. Get real-time search trends, filter by location, category, and time range, and scale effortlessly.
Agent harness to publish your history from Claude Code et al. as Huggingface datasets.
General-purpose planning and execution harness for LLMs — structured phases, critique, gating, and review
🗃 Open source self-hosted web archiving. Takes URLs/browser history/bookmarks/Pocket/Pinboard/etc., saves HTML, JS, PDFs, media, and more...