Search

Kubernetes pod exec plugin for Tabby — no kubectl binary required at runtime

Self-contained visual regression testing for Storybook stories running on Vitest browser mode

Mixed-precision quantization allocator for LLMs: every layer refracts into a different format based on its sensitivity.

Server-side TypeScript client for the multi-backend storage-api ConnectRPC service (local filesystem, Google Cloud Storage, Google Drive, in-memory) over a UNIX domain socket.

Code coverage (line, function, and when/if branch) for Gren node applications

Simple CLI to chat with GGUF models locally (no Ollama/LM Studio required)

Convert Any file Into Anything - one command to convert files between formats, a dispatcher over Docling, Calibre, MarkItDown, faster-whisper, FFmpeg and ImageMagick.

Prove which open model can replace your closed one — on your traffic, your hardware, your budget.

Offensive and defensive AI/LLM security tools, labs and CTF research. Core tools are Python stdlib only.

Local-first, privacy-preserving genealogy CLI with modular LLM providers.

Fairness definitions and bias metrics for large language models

也是一个封装 localStorage 和 sessionStorage 的轻量级工具

Kernel dispatch for PyTorch: torch references, optimized backends, autogenerated correctness and benchmarks.

A lightweight, highly configurable RAG retrieval engine. Framework-free, protocol-driven.

Wrap custom generate function as an OpenAI SDK compatible API service.

The MAIC pluggable persistence layer: KV / asset primitives with swappable backends (browser default, HTTP later), depending only on @openmaic/dsl.

Interactive shell and CLI for llm4ts: flow discovery, run-a-flow, and view

List and resume Claude Code, Codex, Antigravity, and Copilot CLI sessions from one place

Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop

Skill para quitar los rasgos de IA de textos en español, con cobertura de todas las variedades del idioma. Adaptación al español de Stop Slop.