-
Amazon Inc
- San Mateo, CA
- All languages
- Bikeshed
- Blade
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Common Lisp
- Cuda
- Cython
- D
- Dart
- Dockerfile
- Elixir
- Elm
- Emacs Lisp
- Erlang
- FreeMarker
- Go
- Go Template
- Groovy
- HCL
- HTML
- Haskell
- Java
- JavaScript
- Jinja
- Jsonnet
- Julia
- Jupyter Notebook
- Kotlin
- Lua
- MDX
- Makefile
- Markdown
- Mojo
- OCaml
- Objective-C
- Objective-C++
- Perl
- Python
- R
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Starlark
- Swift
- TSQL
- TeX
- Terra
- TypeScript
- Vim Script
- Vue
- WebAssembly
Starred repositories
Apache Ossie, industry wide specification effort to standardize how we exchange semantic metadata across analytics, AI and BI platforms, providing a vendor neutral, single source of truth for seman…
DeepSeek Harness: Everything is a Plugin.
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Low-level unprivileged sandboxing tool used by Flatpak and similar projects
OpenShell is the safe, private runtime for autonomous AI agents.
Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.
Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
A coding agent for open models like Kimi K3
cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign languag…
Production-grade engineering skills for AI coding agents.
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-writ…
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
📰 Must-read papers and blogs on Speculative Decoding ⚡️
HTML is the new markdown. Lavish is the new editor for your HTML artifacts.
Powerful system-level package manager for Linux, macOS and Windows written in Rust – building on top of the Conda ecosystem.
This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction
A minimal, secure Python interpreter written in Rust for use by AI
A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...
Actix Web is a powerful, pragmatic, and extremely fast web framework for Rust.
Teams-first Multi-agent orchestration for Claude Code
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
A vector index built on TurboQuant, written in Rust with Python bindings