InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Ollama

    Models

    Runs open models such as gpt-oss, Qwen and DeepSeek on your own computer.

    Hand-checked InnerVault (hand-checked), Ollama 186.7k ★MIT

    curl -fsSL https://ollama.com/install.sh | sh
  2. llama.cpp

    Models

    The C/C++ engine many local-model tools are built on. It runs models efficiently on ordinary hardware.

    Hand-checked InnerVault (hand-checked), ggml-org MIT

  3. text to image model by RunDiffusion · diffusers

    Stale Hugging Face Hub, RunDiffusion 486 ♥creativeml-openrail-mUpdated 6 months ago

    RunDiffusion/Juggernaut-XL-v9
  4. image to video model by RuneXX · ltx

    Stale Hugging Face Hub, RuneXX 883 ♥Updated 2 months ago

    RuneXX/LTX-2.3-Workflows
  5. The hardest reasoning and long-running work: multi-step decisions and projects that run for hours.

    No longer listed AETHER official model feed, Anthropic Updated 2 months ago

  6. GPT-6 Luna

    Models

    Focused, high-volume tasks where speed and running cost matter most.

    Indexed AETHER official model feed, OpenAI Updated 55 days ago

  7. Gemma 4

    Models

    Open model that can run on your own hardware; reads text, images and audio.

    No longer listed AETHER official model feed, Google Updated 7 months ago

  8. The fastest Claude model: high-volume replies and routing at a low running cost.

    No longer listed AETHER official model feed, Anthropic Updated 13 months ago

  9. Reasoning with quicker answers and lower running cost than Carbon, for everyday agents and analysis.

    Indexed AETHER official model feed, Google Updated 34 days ago

  10. Open (Apache 2.0) model for chat, reasoning and coding that can run privately.

    No longer listed AETHER official model feed, Mistral AI Updated 8 months ago

  11. Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...

    Indexed OpenRouter model list, anthropic Updated 2 months ago

    anthropic/claude-fable-5.1
  12. Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

    Indexed OpenRouter model list, qwen Updated 3 months ago

    qwen/qwen3.8-27b
  13. Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

    Indexed OpenRouter model list, anthropic Updated 9 months ago

    anthropic/claude-opus-4.6
  14. Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...

    Indexed OpenRouter model list, anthropic Updated 2 months ago

    anthropic/claude-fable-5.1:batch
  15. Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...

    Indexed OpenRouter model list, anthropic Updated 7 months ago

    anthropic/claude-opus-4.7
  16. Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

    Indexed OpenRouter model list, anthropic Updated 9 months ago

    anthropic/claude-opus-4.6:batch
  17. Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

    Indexed OpenRouter model list, qwen Updated 3 months ago

    qwen/qwen3.8-27b:batch
  18. Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

    Indexed OpenRouter model list, x-ai Updated 56 days ago

    x-ai/grok-4.7
  19. Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...

    Indexed OpenRouter model list, meta Updated 2 months ago

    meta/muse-spark-1.3
  20. Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...

    Indexed OpenRouter model list, anthropic Updated 7 months ago

    anthropic/claude-opus-4.7:batch
  21. Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

    Indexed OpenRouter model list, x-ai Updated 56 days ago

    x-ai/grok-4.7:batch
  22. GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...

    Indexed OpenRouter model list, openai Updated 11 months ago

    openai/gpt-5.1-codex-max
  23. Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your...

    Indexed OpenRouter model list, typesafe Updated 52 days ago

    typesafe/jev-router

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.