- All languages
- ANTLR
- ASL
- Assembly
- Ballerina
- Batchfile
- C
- C#
- C++
- CMake
- CSS
- Clojure
- CoffeeScript
- Common Lisp
- Crystal
- Cuda
- Dart
- Elixir
- Emacs Lisp
- Erlang
- Go
- HTML
- Handlebars
- Haskell
- Idris
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Lua
- MDX
- Makefile
- Markdown
- Mojo
- Nim
- OCaml
- Objective-C
- PHP
- PLpgSQL
- PowerShell
- Python
- Racket
- Rich Text Format
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Starlark
- Swift
- TeX
- TypeScript
- V
- Vim Script
- Vue
- WebAssembly
- Zig
Starred repositories
Python tool for converting files and office documents to Markdown.
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
A tool to write JS libraries using AI. The first and only tool that is using ASTs to perform surgical changes to existing code files with out mangling the code. https://aicoderproject.com/
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
Limbo is a work-in-progress, in-process OLTP database management system, compatible with SQLite.
A simple, fast, and fun package for building command line apps in Go
A tool for exploring each layer in a docker image
Support for matching file paths against Unix shell style patterns.
We write your reusable computer vision tools. 💜
A new markup-based typesetting system that is powerful and easy to learn.
Heapless, `static` friendly data structures
Asynchronous streams for Rust using async & await notation
Cloud-native search engine for observability. An open-source alternative to Datadog, Elasticsearch, Loki, and Tempo.
Open-source vector similarity search for Postgres
A modular graph-based Retrieval-Augmented Generation (RAG) system
Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
Distribute and run LLMs with a single file.
AGI's query engine - Platform for building AI that can learn and answer questions over federated data.
Performance-portable, length-agnostic SIMD with runtime dispatch
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production