- Berlin / Brooklyn / LA
- http://jeff-kao.com
Stars
- All languages
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Cuda
- Dart
- Dockerfile
- Elixir
- Go
- HCL
- HTML
- Haskell
- Java
- JavaScript
- Jupyter Notebook
- Kotlin
- Less
- Lua
- MDX
- Makefile
- Markdown
- Objective-C
- PHP
- Perl
- Python
- R
- RenderScript
- Rich Text Format
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Svelte
- Swift
- Twig
- TypeScript
- Vim Script
- Vue
- Zig
Robust Speech Recognition via Large-Scale Weak Supervision
The Web framework for perfectionists with deadlines.
Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
Scrapy, a fast high-level web crawling & scraping framework for Python.
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
LlamaIndex is the leading document agent and OCR platform
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
🎨 Diagram as Code for prototyping cloud system architectures
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
You like pytorch? You like micrograd? You love tinygrad! ❤️
Build resilient language agents as graphs.
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
Distributed Task Queue (development branch)
Code for the paper "Language Models are Unsupervised Multitask Learners"
The leading data integration platform for ETL / ELT data pipelines from APIs, databases & files to data warehouses, data lakes & data lakehouses. Both self-hosted and Cloud-hosted.
Zipline, a Pythonic Algorithmic Trading Library
Luigi is a Python module that helps you build complex pipelines of batch jobs. It handles dependency resolution, workflow management, visualization etc. It also comes with Hadoop support built in.
An extremely fast Python type checker and language server, written in Rust.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
match command-line arguments to their help text
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
The open-source AIOps and alert management platform
q - Run SQL directly on delimited files and multi-file sqlite databases