macOS and Linux VMs on Apple Silicon to use in CI and other automations

The open-source SDK for bringing any agent into any chat platform: Slack, Microsoft Teams, Discord, Telegram - with native, Interactive UI.

IP addresses break, dial keys instead. A library that adds QUIC + NAT Traversal to your apps.

Prose diffs for any document format supported by Pandoc

A multi-hypervisor VM runtime for OCI images, supporting Cloud Hypervisor, Firecracker, QEMU, and Apple Virtualization.framework.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

A browser that runs directly inside your existing terminal

Safe interop between Rust and C++

A workspace-aware Cargo lint for unnecessary public Rust APIs.

A batteries-included framework for building web apps

Unofficial Rust bindings to Apple's mlx framework

Inferno aims to be a super lightweight, highly efficient Rust inference engine for running open weights models on Apple Silicon with Metal, targeting machines such as a MacBook Pro with 64 GB of un…

Open-weight emotion and refusal vector extraction and steering experiments.

Multi-platform high-performance compute language extension for Rust.

Democratizing large model inference and training on any device.

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

Fast, flexible LLM inference

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…

Generate @effect/schema definitions from an OpenAPI document

pierre’s open source code

Infrastructure as Effects

Here are some skills I use. Maybe you'll find them useful. Maybe not. Goodbye.

Bonsai Demo

LLM inference in C/C++

Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, and structured output. Supports vLLM, SGLang, and llama.cpp.

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Measuring frontier coding agents on original, long-horizon engineering tasks