InnerVault

Library

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

Results

7,862 results with any of your words Clear search and filters
  1. automatic speech recognition model by nvidia · nemo

    Stale Hugging Face Hub, nvidia 33 ♥otherUpdated 21 days ago

    nvidia/nemotron-labs-unified-asr-0.6b
  2. Class Prep

    Prompts

    I want a prompt that can help be prepare my understanding and get comfortable with the learning input before class starting.

    Indexed prompts.chat (CC0 prompt collection), master.at909@gmail.com CC0-1.0

  3. I want you to act as a Motion Designer specializing in "Cybernetic Data Streams"—visualizing complex data flows using 3D particle lines and nodes. Vision: Design a 3D "Network Topology" where particles travel along…

    Indexed prompts.chat (CC0 prompt collection), loshu2000 CC0-1.0

  4. Soup

    AI repositories

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    Stale GitHub, MakazhanAlpamys 10.3k ★Apache-2.0Updated 10 days ago

    git clone https://github.com/MakazhanAlpamys/Soup.git
  5. DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

    Indexed OpenRouter model list, deepseek Updated 14 months ago

    deepseek/deepseek-v3.1-terminus
  6. Z.ai: GLM 4.5

    Models

    GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

    Indexed OpenRouter model list, z-ai Updated 16 months ago

    z-ai/glm-4.5
  7. Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

    Indexed OpenRouter model list, qwen Updated 16 months ago

    qwen/qwen3-235b-a22b-thinking-2507
  8. Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...

    No longer listed OpenRouter model list, xingchen-agi Updated 32 days ago

    xingchen-agi/xing4.0-29b-a4b:free
  9. Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

    Indexed OpenRouter model list, morph Updated 16 months ago

    morph/morph-v3-fast:batch
  10. alpha-stream-mcp

    MCP servers

    Stateful 5-minute delta feed for autonomous trading bots: computes real-time shifts in DEX buy/sel

    Stale Official MCP Registry, io.github.robertoyanguas-ops Updated 29 days ago 1 note

  11. ROLE: Travel Planner INPUT: - Destination: ${city} - Dates: ${dates} - Budget: ${budget} + currency - Interests: ${interests} - Pace: ${pace} - Constraints: ${constraints} TASK: 1) Ask clarifying questions if needed…

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

  12. Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

    Indexed OpenRouter model list, qwen Updated 15 months ago

    qwen/qwen3-30b-a3b-instruct-2507
  13. EncodeX

    MCP servers

    A free and open-source multimedia toolkit built on FFmpeg. Convert, compress, extract, cut and batch-process audio, video and images, or drive the same engine from the CLI, an MCP server or the AI Copilot.

    Stale GitHub, Sandeepv68 22 ★MITUpdated 10 days ago

    git clone https://github.com/Sandeepv68/EncodeX.git
  14. SUNGLASSES

    MCP servers

    Input firewall for AI agents: scan text and files before they're read. Local, no network by default.

    Indexed Official MCP Registry, io.github.sunglasses-dev Updated 2 days ago 1 note

    sunglasses@0.6.24
  15. GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

    Indexed OpenRouter model list, z-ai Updated 16 months ago

    z-ai/glm-4.5-air
  16. Emotion Analyst

    Prompts

    Act as an Emotion Analyst. You are an expert in analyzing human emotions from text input. Your task is to identify underlying emotional tones and provide insights. You will: - Analyze text for emotional content. -…

    Indexed prompts.chat (CC0 prompt collection), kjkjw5@gmail.com CC0-1.0

  17. Pokemon master

    Prompts

    Take the input image, and use it is face and apply it to be Ash the Pokemon master image with his favorite character pikachu.

    Indexed prompts.chat (CC0 prompt collection), f4p4yd1n@gmail.com CC0-1.0

  18. gemini-android

    AI repositories

    ✨ Gemini Android demonstrates Google's Generative AI on Android with Stream Chat SDK for Compose.

    Stale GitHub, GetStream 387 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/GetStream/gemini-android.git
  19. River levels & flood alerts: USGS gauges. $0.01/query. Be born in one call — free testnet funds.

    Stale Official MCP Registry, com.a2awire Updated 9 days ago 1 note

  20. inferssd

    AI repositories

    Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

    Indexed GitHub, wici-ai 1,025 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/wici-ai/inferssd.git
  21. Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

    Indexed OpenRouter model list, qwen Updated 3 months ago

    qwen/qwen3.8-2.4t-a95b
  22. Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

    Indexed OpenRouter model list, aion-labs Updated 21 months ago

    aion-labs/aion-rp-llama-3.1-8b
  23. Stateful 5-minute delta feed for autonomous trading bots: computes real-time shifts in DEX buy/se.

    Stale Official MCP Registry, dev.agentdiet Updated 27 days ago 1 note

  24. Build an interactive typing speed test using HTML5, CSS3, and JavaScript. Create a clean interface with text display and input area. Implement WPM and accuracy calculation in real-time. Add difficulty levels with…

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