Back to directory

ShadowQuill

A local, offline prompt-engineering studio that turns rough ideas into structured prompts using self-hosted Gemma models through Ollama, with no cloud API, account or network access required after setup.

ShadowQuill

ShadowQuill is a local prompt studio that turns rough ideas into structured prompts, running entirely against Ollama and locally hosted Google Gemma models with no cloud API call, account or network access needed once it is set up. It offers eight tabs for keeping several prompts open at once, seven task types covering intent, engineering, visual, motion, analysis, narrative and persuasion prompts, ten default presets as starting points for common workflows, a Preset Studio for building custom presets with a live preview, and version history for stepping back and forward through a prompt's revisions.

Setup requires Ollama installed locally with at least one Gemma model pulled, after which the app is installed and run with pnpm. Projects, presets and configuration are stored only on the local disk, and the project states that it sends no telemetry.

It is built with Next.js, Electron, React and TypeScript, and is MIT licensed.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.