Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
LFM2-Audio-1.5B
Modelsaudio to audio model by LiquidAI · liquid-audio
LiquidAI/LFM2-Audio-1.5B -
Awesome-RAG
AI repositories💡 Awesome RAG: A resource of Retrieval-Augmented Generation (RAG) for LLMs, focusing on the development of technology.
git clone https://github.com/liunian-Jay/Awesome-RAG.git -
Timestral-123M
Modelstime series forecasting model by mistralai · timestral
mistralai/Timestral-123M -
verbalized-sampling
PromptsVerbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.
git clone https://github.com/CHATS-lab/verbalized-sampling.git -
distil-large-v3
Modelsautomatic speech recognition model by distil-whisper · transformers
distil-whisper/distil-large-v3 -
clip-vit-large-patch14-336
Modelszero shot image classification model by openai · transformers
openai/clip-vit-large-patch14-336 -
text generation model by TheBloke · transformers
TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ -
LTX-2.3
Modelsimage to video model by Lightricks · diffusers
Lightricks/LTX-2.3 -
text to image model by KasugaiSakura · gguf
KasugaiSakura/Qwen-Image-2.1-Uncensored-Abenzerps-GGUF -
MiroThinker
Agents & frameworksMiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
git clone https://github.com/MiroMindAI/MiroThinker.git -
ChatArena
Agents & frameworksChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
git clone https://github.com/Farama-Foundation/ChatArena.git -
model by madebyollin · diffusers
madebyollin/texture-fix-vae-for-qwen-image-2.1 -
DyCodeEval
Datasets & benchmarksOfficial repository of the ICML2025 paper “Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination”
git clone https://github.com/SeekingDream/DyCodeEval.git -
GoNavi
MCP serversHigh-performance multi-data-source database client — ~30MB, AI & MCP ready, zero Electron bloat. | 高性能多数据源数据库客户端:约 30MB,AI 与 MCP 就绪,告别 Electron 膨胀。
git clone https://github.com/Syngnat/GoNavi.git -
animagine-xl
Modelstext to image model by Linaqruf · diffusers
Linaqruf/animagine-xl -
DeepSeek-V3.1-Terminus
Modelstext generation model by deepseek-ai · transformers
deepseek-ai/DeepSeek-V3.1-Terminus -
whistle
Modelsautomatic speech recognition model by Cactus-Compute · cactus-compute
Cactus-Compute/whistle -
Qwen3.8-Flash-Next-FP8
Modelsimage text to text model by Qwen · transformers
Qwen/Qwen3.8-Flash-Next-FP8 -
ReForm-Eval
Datasets & benchmarksAn benchmark for evaluating the capabilities of large vision-language models (LVLMs)
git clone https://github.com/FudanDISC/ReForm-Eval.git -
FLUX.1-dev-IP-Adapter
Modelstext to image model by InstantX · diffusers
InstantX/FLUX.1-dev-IP-Adapter -
BrickGPT
AI repositories[ICCV 2025 Best Paper] Official repository for BrickGPT, the first approach for generating physically stable toy brick models from text prompts.
git clone https://github.com/AvaLovelace1/BrickGPT.git -
EmbedAnything
AI repositoriesHighly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀
git clone https://github.com/StarlightSearch/EmbedAnything.git -
imixs-workflow
Tools & appsThe open source technology for business process management
git clone https://github.com/imixs/imixs-workflow.git -
ZONOS3-Mini
Modelstext to speech model by Zyphra · zonos3
Zyphra/ZONOS3-Mini
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.