InnerVault

Library

85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.

Results

862 results with any of your words Clear search and filters
  1. mockbird

    Skills

    Four Agent Skills that stop AI agents from shipping generic UI: a screen canvas with real interactive HTML mockups, per-project design system, validator and a self-updating OpenCode v2 plugin.

    Stale GitHub, misereitor 5 ★MITUpdated 10 days ago

    git clone https://github.com/misereitor/mockbird.git
  2. crux

    Skills

    A scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki, a task manager, and a local browser GUI cockpit.

    Stale GitHub, mehdiforoozandeh 18 ★MITUpdated 17 days ago

    git clone https://github.com/mehdiforoozandeh/crux.git
  3. NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    Indexed OpenRouter model list, nvidia Updated 5 months ago

    nvidia/nemotron-3-ultra-550b-a55b
  4. Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

    No longer listed OpenRouter model list, stepfun Updated 9 months ago

    stepfun/step-3.5-flash
  5. Spec Interview

    Prompts

    read this${specmd:spec.md} and interview me in detail using the AskUserQuestionTool (or similar tool) about literally anything: technical implementation, UI & UX, concerns, tradeoffs, etc. but make sure the questions…

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

  6. Act as a critical research analyst specializing in literature reviews and research gap identification. Your goal is to help me identify meaningful, researchable gaps in a specific field by analyzing existing research…

    Indexed prompts.chat (CC0 prompt collection), Priyanshu3221 CC0-1.0

  7. NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    Indexed OpenRouter model list, nvidia Updated 5 months ago

    nvidia/nemotron-3-ultra-550b-a55b:free
  8. Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

    Indexed OpenRouter model list, moonshotai Updated 12 months ago

    moonshotai/kimi-k2-thinking
  9. Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

    Indexed OpenRouter model list, moonshotai Updated 14 months ago

    moonshotai/kimi-k2-0905
  10. Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

    No longer listed OpenRouter model list, tencent Updated 16 months ago

    tencent/hunyuan-a13b-instruct
  11. MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...

    No longer listed OpenRouter model list, minimax Updated 17 months ago

    minimax/minimax-m1
  12. --- description: "[V2] AI study assistant that transforms lectures into high-fidelity, structured notes. Optimized for AI Blaze with strict YAML schema, forcing functions, and quality gates." --- # GENERATIVE AI STUDY…

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

  13. Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

    Indexed OpenRouter model list, meta-llama Updated 19 months ago

    meta-llama/llama-4-scout
  14. Act as a Pharmacy Research Assistant. You are an expert in supporting pharmaceutical research teams with cutting-edge insights and data. Your task is to: - Conduct comprehensive literature reviews on ${topic} - Analyze…

    Indexed prompts.chat (CC0 prompt collection), jiayuehuang765@gmail.com CC0-1.0

  15. # Role You are a deterministic Localizable Strings Parser and Translator. Your job is to translate string literals without affecting code structure. # Execution Paradigm 1. Treat the input file as a Key-Value database…

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

  16. lit crit

    Prompts

    Role: Act as a seasoned literary critic and narrative theorist. Your goal is to perform a deep-tissue deconstruction of the following work:. Analysis Requirements: Please analyze the work through these specific lenses…

    Indexed prompts.chat (CC0 prompt collection), kennynah85@gmail.com CC0-1.0

  17. gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-oss-20b
  18. Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

    Indexed OpenRouter model list, qwen Updated 16 months ago

    qwen/qwen3-coder
  19. Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

    Indexed OpenRouter model list, meta-llama Updated 19 months ago

    meta-llama/llama-4-maverick
  20. Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.

    Indexed OpenRouter model list, kt Updated 12 days ago

    kt/midm-k-3.0-pro
  21. gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-oss-20b:batch
  22. Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...

    Indexed OpenRouter model list, inclusionai Updated 2 months ago

    inclusionai/ling-3.0-flash-vl
  23. *Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

    Indexed OpenRouter model list, inclusionai Updated 3 months ago

    inclusionai/ling-3.0-flash
  24. gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-oss-120b

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.