InnerVault

Library

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

Results

  1. awesome-ai-papers

    Docs & tutorials

    A curated list of the most impressive AI papers

    Stale GitHub, aimerou 1,318 ★Updated 16 months ago

    git clone https://github.com/aimerou/awesome-ai-papers.git
  2. peft

    AI repositories

    🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

    Indexed GitHub, huggingface 21.9k ★Apache-2.0Updated 2 days ago

    git clone https://github.com/huggingface/peft.git
  3. fastembed

    AI repositories

    Fast, Accurate, Lightweight Python library to make State of the Art Embedding

    Stale GitHub, qdrant 3,276 ★Apache-2.0Updated 13 days ago

    git clone https://github.com/qdrant/fastembed.git
  4. llm-d

    AI repositories

    State of the art inference performance with modern accelerators on Kubernetes

    Indexed GitHub, llm-d 5,274 ★Apache-2.0Updated yesterday

    git clone https://github.com/llm-d/llm-d.git
  5. transformers

    AI repositories

    🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

    Indexed GitHub, huggingface 169.0k ★Apache-2.0Updated yesterday

    git clone https://github.com/huggingface/transformers.git
  6. Awesome-Jailbreak-on-LLMs

    AI repositories

    Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

    Stale GitHub, yueliu1999 1,730 ★MITUpdated 9 days ago

    git clone https://github.com/yueliu1999/Awesome-Jailbreak-on-LLMs.git
  7. ailia-models

    AI repositories

    The collection of pre-trained, state-of-the-art AI models for ailia SDK

    Indexed GitHub, ailia-ai 2,405 ★Custom licence (see repository)Updated 4 days ago

    git clone https://github.com/ailia-ai/ailia-models.git
  8. VAR

    AI repositories

    [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

    Stale GitHub, FoundationVision 8,753 ★MITUpdated 12 months ago

    git clone https://github.com/FoundationVision/VAR.git
  9. HypePaper

    MCP servers

    State of the art, trending papers, benchmarks, citations and topic experts from HypePaper.

    Stale Official MCP Registry, app.hypepaper Updated 3 days ago 1 note

  10. megabots

    Prompts

    🤖 State-of-the-art, production ready LLM apps made mega-easy, so you don't have to build them from scratch 🤯 Create a bot, now 🫵

    Stale GitHub, momegas 350 ★MITUpdated 3 years ago

    git clone https://github.com/momegas/megabots.git
  11. graphrag-rs

    AI repositories

    GraphRAG-rs is a high-performance, state-of-the-art Rust implementation of GraphRAG (Graph-based Retrieval Augmented Generation) that builds knowledge graphs from documents and enables natural language querying with configurable entity extraction and local LLM integration

    Indexed GitHub, automataIA 539 ★MITUpdated yesterday

    git clone https://github.com/automataIA/graphrag-rs.git
  12. ocr-mcp

    MCP servers

    FastMCP server providing advanced OCR capabilities with current state-of-the-art models (DeepSeek-OCR, Florence-2, DOTS.OCR, PP-OCRv5, Qwen-Image-Layered decomposition), WIA scanner control, and multi-format document processing for PDFs, CBZ comics, and images.

    Stale GitHub, sandraschi 23 ★MITUpdated 21 days ago

    git clone https://github.com/sandraschi/ocr-mcp.git
  13. big-AGI

    Agents & frameworks

    AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

    Stale GitHub, enricoros 7,167 ★MITUpdated 12 days ago

    git clone https://github.com/enricoros/big-AGI.git
  14. Cloud Document AI API

    Public APIs

    Service to parse structured information from unstructured or semi-structured documents using state-of-the-art Google AI such as natural language, computer vision, translation, and AutoML.

    Indexed APIs.guru OpenAPI Directory, Google Updated 3 years ago

  15. MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

    No longer listed OpenRouter model list, minimax Updated 10 months ago

    minimax/minimax-m2.1
  16. Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/devstral-2512
  17. Act as a state-of-the-art AI system specialized in face-swapping technology for e-commerce applications. Your task is to enable users to visualize e-commerce products using AI face swapping, enhancing personalization…

    Indexed prompts.chat (CC0 prompt collection), Encounterx1 CC0-1.0

  18. Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

    Indexed OpenRouter model list, moonshotai Updated 9 months ago

    moonshotai/kimi-k2.5
  19. Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...

    Indexed OpenRouter model list, google Updated 13 months ago

    google/gemini-2.5-flash-image
  20. Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

    Indexed OpenRouter model list, mistralai Updated 20 months ago

    mistralai/mistral-small-3.1-24b-instruct
  21. Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...

    Indexed OpenRouter model list, mistralai Updated 12 months ago

    mistralai/voxtral-small-24b-2507
  22. Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

    Indexed OpenRouter model list, mistralai Updated 18 months ago

    mistralai/mistral-medium-3
  23. Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

    Indexed OpenRouter model list, google Updated 5 months ago

    google/gemini-3.1-flash-image
  24. Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

    Indexed OpenRouter model list, anthropic Updated 13 months ago

    anthropic/claude-sonnet-4.5

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.