- San Francisco, USA
Stars
- All languages
- ActionScript
- AspectJ
- Assembly
- Awk
- Batchfile
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Dockerfile
- Elixir
- Emacs Lisp
- F#
- Fortran
- Frege
- Go
- HTML
- Haskell
- Java
- JavaScript
- Jupyter Notebook
- Kotlin
- Lua
- M4
- Makefile
- OCaml
- Objective-C
- Objective-C++
- Objective-J
- PHP
- Perl
- Pony
- PowerShell
- Python
- QML
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Scheme
- Shell
- Swift
- TeX
- TypeScript
- Vim Script
- XSLT
Scruff is an experimental, lightweight linter and formatter for Scala, written in Rust
Analyze Rust crates without touching compiler internals
A verification toolchain for Rust programs
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included.
A documentation only view into the inner workings of Claude Code
Declarative UI layout and rendering for no_std targets, inspired by SwiftUI
Modern embedded framework, using Rust and async.
Tool to simplify vector geographical datasets representing tesselations, such as administrative regions, land cover areas, etc.
Stream virtual desktops and games running in Docker
Sunshine fork - The easiest way to stream with the native resolution of your client device
Let your AI agents paint big arrows, boxes and text on your Mac screen. One CLI, click-through, gone by itself. Skill for Claude Code and Codex. MIT.
A local inference engine for Apple silicon, built around the model.
ROS2 Differential Drive Controller for Raspberry Pi Build HAT (a hardware connector for Lego Spike Prime)
Deterministic guardrails that don't break agents
Multiplayer harness that shapes around your work. Agents, apps and workflows your team shares, used from Slack, Telegram, WhatsApp, Teams, Email, Web or your own AI agent.
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
Contrastive Language Models (CLMs) are a new class of System One model trained with a contrastive learning objective that connects states and actions.
High-performance In-browser LLM Inference Engine
HA ecobee integration with Resource Owner Password Grant — bypasses ecobee's shut-down dev portal, exposes per-room remote sensors
open-source canvas for thoughtful software design
One CLI and Jev-compatible API for local and hosted typed-decision backends (planning)
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Batched single-token choice inference for open language models, compatible with TypeSafe