Stars
- All languages
- APL
- Assembly
- Astro
- Awk
- C
- C#
- C++
- CSS
- Cirru
- Clojure
- CoffeeScript
- Common Lisp
- Coq
- Dart
- Elixir
- Elm
- Emacs Lisp
- Erlang
- F*
- Forth
- Fortran
- Go
- HCL
- HTML
- Haskell
- Haxe
- JSONiq
- Java
- JavaScript
- Jupyter Notebook
- Kotlin
- LLVM
- Lean
- Lua
- Makefile
- Mathematica
- Nim
- OCaml
- Objective-C
- OpenSCAD
- PHP
- PLSQL
- PLpgSQL
- Perl
- Pony
- Prolog
- PureScript
- Python
- QML
- R
- Racket
- Red
- Rich Text Format
- Ruby
- Rust
- SVG
- Scala
- Scheme
- Shell
- Smalltalk
- Smarty
- Standard ML
- Svelte
- Swift
- TLA
- TSQL
- TeX
- TypeScript
- Vim Script
- Zig
- wisp
Creating an AI agent with LISP - the 2026 version of what made LISP "the language for AI" in the first place
Claude Code skill for product videos: real browser capture, branded composition, and local mastering.
Postgres rewritten in Rust, now faster than Postgres and Clickhouse
The whole Earth in 3D, for Mac with Apple silicon. Downloads, screenshots and issue reports.
Holochain hApp for epistemic discourse: claims/critiques/evidence graphs, Promise Theory validation, web-of-trust attestation, and a Twitter correlative-witness bridge.
Programming tools can now be transmitted in the form of prompts instead of finished software. Here's a library of such tool seeds.
Embedded graph memory for AI agents, mobile apps, and the browser.
Hops Run, a low-poly racer, and the decision models served on Hopsworks that fly it live
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
A text diagram language where you say where things go. Playground: reladraw.github.io/reladraw
A small, fast array language that talks like q: tables, the whole join family, qSQL, tick data and dates, in one little C binary. Built on ngn/k.
A Datalog triplestore on top of SlateDB with support for history and incremental queries
Talk to your coding agent from a phone browser. Local speech in and out, no app, no GPU.
use 2D Gaussian splats to paint a version of the input image
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C infe…
Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.
Lightweight text-based SQL parameter binds using t-strings
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center