🎙️ Give your apps, CLIs, and agents a voice. VoiPi is a universal, zero-dependency, free text-to-speech library for JavaScript.

ArtifactFS is a filesystem driver designed to mount large git repos as quickly as possible, hydrating file contents on-the-fly instead of blocking on the initial clone. It's ideal for agents, sandb…

Agent Skill to help convert transformer LLMs to mlx-lm

KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.

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

Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"

Lucebox optimization hub: hand-tuned LLM inference, built for specific consumer hardware.

Lossless DFlash speculative decoding for MLX on Apple Silicon

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

Static checker for GitHub Actions workflow files

Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.

The Modular Platform (includes MAX & Mojo)

nono - a capability-based, multiplexing sandbox tool, built for developers - lift'n'shift seamless path to prod. Run agents securely without needing any additional infra, zero setup, zero latency.

Full-screen TUI worktree manager in Rust

Replace port numbers with stable, named local URLs. For humans and agents.

Dark mode PDFs without destroying your images.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.

Running a big model on a small laptop

Train the smallest LM you can that fits in 16MB. Best model wins!

Sub-millisecond VM sandboxes for AI agents via copy-on-write forking

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

Lean 4 programming language and theorem prover

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

sub-500ms latency phone agent orchestration

Secure and fast microVMs for serverless computing.