Lightning fast hash functions using hand-tuned WebAssembly binaries

Cells is a lightweight spreadsheet engine, with CLI and web interface.

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

MailCore 2 provide a simple and asynchronous API to work with e-mail protocols IMAP, POP and SMTP. The API has been redesigned from ground up.

Speak Friend, and Enter

macOS 26+ browser CLI for agents: persistent sessions, compact JSON, screenshots, clicks/forms, JS eval, and live preview in under 2 MB.

CLI to manage emails

PostgreSQL driver and toolkit for Go

The official Go library for the OpenAI API

Access to Anthropic's safety-first language model APIs via Go

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…

Programmable spreadsheet platform with a TypeScript/Rust engine, SDK, and embeddable workbook runtime.

A blazingly fast Slack TUI

Secure-by-design and flexible Unix socket proxy. Built in memory-safe Go with zero dependencies, no shell or interpreter required in containers. A modern alternative to tecnativa/docker-socket-prox…

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

Lightweight coding agent that runs in your terminal

Can Language Models Rebuild Programs From Scratch?

Safe, UNIX-like mini-OS capsules for agents, designed to run across Linux, macOS, Windows, web browsers, iOS, and Android.

Procedural generation with diffusion models (SIGGRAPH '26)

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

A HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.

A refreshingly simple data-driven game engine built in Rust

Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates.

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Fast, accurate & comprehensive text measurement & layout

IDE for parallel agent work. Create worktrees in one click. Share plans between agents. Execute with parallelism + isolation.

Terminal-native AI coding agent running in containers.

⚡ preexec and precmd functions for Bash just like Zsh.