InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. localharness

    Agents & frameworks

    An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harness (detailed event steams, logs, and performance data) or quickly replace closed source one (featuring out of the box plugins for web search, image gen, memory, auto research and more in dev).

    Stale GitHub, ahwurm 59 ★MITUpdated 12 days ago

    git clone https://github.com/ahwurm/localharness.git
  2. Use the person from the uploaded photo as the primary reference. Keep facial features, hair, skin tone, and overall identity identical (no beautification, no age changes). Scene: Modern corporate studio portrait shoot…

    Indexed prompts.chat (CC0 prompt collection), semihkislar CC0-1.0

  3. Use the uploaded photo of the person as the main subject. Preserve the person’s REAL face, facial features, skin tone, hairstyle, and identity exactly as in the original photo. Do not change age or facial structure…

    Indexed prompts.chat (CC0 prompt collection), semihkislar CC0-1.0

  4. Present a clear, 45° top-down view of a vertical (9:16) isometric miniature 3D cartoon scene, highlighting iconic landmarks centered in the composition to showcase precise and delicate modeling. The scene features…

    Indexed prompts.chat (CC0 prompt collection), mehmetaltugakgul CC0-1.0

  5. Develop a creative dice generator called “IdeaDice”. Features an eye-catching industrial-style interface, with a fluorescent green title prominently displayed at the top of the page:🎲“IdeaDice · Inspiration Throwing…

    Indexed prompts.chat (CC0 prompt collection), loshu2003@gmail.com CC0-1.0

  6. Transform the subject or image into a cute plush form with soft textures and rounded shapes. If the image contains a human, preserve the distinctive features so the subject remains recognizable. Otherwise, turn the…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  7. # React / Next.js Frontend Architect You are a Senior React Frontend Engineer specializing in React 19, Next.js 15 App Router, TypeScript, Redux Toolkit, RTK Query, Node.js integration, Feature-Sliced Design (FSD)…

    Indexed prompts.chat (CC0 prompt collection), dh92fr@gmail.com CC0-1.0

  8. agent-afk

    MCP servers

    The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s done. You come back to a receipt of every step, every decision, and what’s waiting on you. If it’s unsure, it stops and asks instead of guessing.

    Indexed GitHub, griffinwork40 63 ★Apache-2.0Updated today

    git clone https://github.com/griffinwork40/agent-afk.git
  9. devcycle

    Skills

    Turns a short feature/bug description into a reviewed, on-device-verified implementation — parallel subagents, cross-model review, GitHub reconcile, and a doctor/learn loop that benchmarks and improves the pipeline itself. Built on superpowers.

    Indexed GitHub, KonstantinRoehrl 5 ★MITUpdated 3 days ago

    git clone https://github.com/KonstantinRoehrl/devcycle.git
  10. Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

    Indexed OpenRouter model list, qwen Updated 6 months ago

    qwen/qwen3.6-27b
  11. Act as an image generation expert. Your task is to create studio images featuring a host in different professional postures. You will: - Insert the host into a modern studio setting with realistic lighting. - Ensure…

    Indexed prompts.chat (CC0 prompt collection), frosjah@gmail.com CC0-1.0

  12. Present a clear, 45° top-down view of a vertical (9:16) isometric miniature 3D cartoon scene, highlighting iconic landmarks centered in the composition to showcase precise and delicate modeling. The scene features…

    Indexed prompts.chat (CC0 prompt collection), cakmakbatuhan@gmail.com CC0-1.0

  13. An ultra-realistic 8K cinematic studio portrait framed from mid-thigh up, featuring a figure standing confidently against a vibrant ochre-red background. The subject wears an oversized, highly textured bomber jacket…

    Indexed prompts.chat (CC0 prompt collection), kemalersin CC0-1.0

  14. Train Waiter

    Prompts

    A 3x2 grid photo contact sheet featuring a consistent 28-year-old American woman with a specific facial structure, wearing a jacket and outdoor pants, in a train station at dusk with dramatic orange and teal lighting…

    Indexed prompts.chat (CC0 prompt collection), kakekgaek65@gmail.com CC0-1.0

  15. Act as a Creative Application Namer. You are skilled in crafting engaging and memorable names for digital applications. Your task is to create a unique name for a computer application that features a customizable…

    Indexed prompts.chat (CC0 prompt collection), daiwhmiao CC0-1.0

  16. PORTRAIT

    Prompts

    A 20-year-old adult American female model with fair skin wears a short feathered crop with airy layers around the ears and a deliberately tousled crown. She wears a translucent lime-green asymmetric top and holds a…

    Indexed prompts.chat (CC0 prompt collection), talkjignesh@gmail.com CC0-1.0

  17. Full-body vertical photograph of a stunning young woman with long straight light-brown hair, tanned golden skin, delicate facial features, full lips, and an extremely curvaceous hourglass figure with a very narrow…

    Indexed prompts.chat (CC0 prompt collection), alejandro.garcia.garay@gmail.com CC0-1.0

  18. Create a vertical 9:16 collage with exactly 3 clearly separated equal panels stacked vertically. The same adult Japanese woman appears in all three panels with identical facial features and identity. TOP PANEL…

    Indexed prompts.chat (CC0 prompt collection), alejandro.garcia.garay@gmail.com CC0-1.0

  19. A rich, atmospheric vertical medium shot featuring two cosplayers in detailed costumes against a deep, completely black background, creating a sense of isolation and darkness. The female cosplayer stands with her back…

    Indexed prompts.chat (CC0 prompt collection), alejandro.garcia.garay@gmail.com CC0-1.0

  20. Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

    Indexed OpenRouter model list, google Updated 7 months ago

    google/gemma-4-31b-it
  21. GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

    Indexed OpenRouter model list, openai Updated 8 months ago

    openai/gpt-5.4
  22. Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/mistral-large-2512
  23. Create an image for a hero section with a 16:9 aspect ratio. The image should feature 6-7 different types of plants, all set in a natural environment with sunlight streaming in. Make sure the composition is…

    Indexed prompts.chat (CC0 prompt collection), gurkankaya05 CC0-1.0

  24. Act as a professional photo editor. Your task is to enhance the beauty and quality of the uploaded photo. You will: - Adjust brightness and contrast for optimal clarity. - Smooth skin tones and enhance facial features…

    Indexed prompts.chat (CC0 prompt collection), coursellebryan@gmail.com CC0-1.0

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.