AI Tools Collection
One-stop directory of AI models, skills and MCP tools — search and find the AI that suits you.
AI Model · speech-enhancement
All (20)sepformer wham16k enhancement
AI ModelThe SepFormer WHAM!16k is a specialized speech enhancement model designed to isolate clean voice signals from
sepformer dns4 16k enhancement
AI ModelSepFormer DNS4 16k is a specialized speech enhancement model designed to isolate clean voice signals from nois
sepformer whamr enhancement
AI ModelSepFormer WHAMR is a specialized speech enhancement model designed to isolate clean speech from complex, noisy
sepformer wham enhancement
AI ModelSepFormer WHAM is a specialized speech enhancement model designed to isolate target speech from complex, noisy
speech enhancement sgmse
AI ModelSGMSE is a generative speech enhancement model designed to isolate clean voice signals from noisy environments
mpse smoe speech enhancement
AI ModelMPSE SMOE is a specialized speech enhancement model designed to isolate clean vocals from noisy environments.
unet speech enhancement
AI ModelThe UNet Speech Enhancement model is a deep learning architecture designed to isolate target speech from compl
speech enhancement mask unet
AI ModelThe Speech Enhancement Mask UNet is a deep learning architecture designed to isolate clean speech from noisy b
AI Model · text-to-video
All (19)Sulphur 2 base
AI ModelSulphur 2 base is a foundational text-to-video model designed for developers building generative media pipelin
Wan2.2 TI2V 5B Diffusers
AI ModelWan2.2 TI2V 5B is a specialized image-to-video diffusion model designed for high-fidelity temporal animation.
Wan2.1 T2V 1.3B Diffusers
AI ModelWan2.1 T2V 1.3B is a lightweight text-to-video diffusion model optimized for efficiency and accessibility. Unl
MiniMax H3 Turbo Lora ComfyUI
AI ModelThe MiniMax H3 Turbo LoRA for ComfyUI brings professional-grade text-to-video generation directly into a modul
Sulphur 2 base GGUF
AI ModelSulphur 2 Base GGUF provides developers with a quantized, hardware-efficient implementation of the Sulphur 2 a
Wan2.2 T2V A14B Diffusers
AI ModelWan2.2 T2V A14B is a high-capacity text-to-video diffusion model designed for developers seeking a balance bet
Wan2.2 T2V A14B GGUF
AI ModelWan2.2 T2V A14B GGUF provides a quantized implementation of the 14-billion parameter text-to-video model, spec
FastWan2.2 TI2V 5B FullAttn Diffusers
AI ModelFastWan2.2 TI2V 5B is a specialized Text-to-Image-to-Video (TI2V) diffusion model designed for high-fidelity c
AI Model · text-generation
All (18)Llama 3.1 405B
AI ModelOpen source large language model
Mixtral 8x7B
AI ModelSparse mixture of experts model
Qwen3 0.6B
AI ModelQwen3 0.6B is a highly compact language model designed for efficiency and low-latency deployment. At under one
Qwen3 8B
AI ModelQwen3 8B is a compact yet powerful language model designed for high-efficiency deployment without sacrificing
tiny Qwen2ForCausalLM 2.5
AI ModelThe tiny Qwen2ForCausalLM 2.5 is a compact, efficient language model designed for low-latency applications and
gpt2
AI ModelGPT-2 is a foundational transformer-based language model that marked a shift toward zero-shot learning in NLP.
Qwen2.5 7B Instruct
AI ModelQwen2.5 7B Instruct is a dense decoder-only model designed for high-efficiency deployment without sacrificing
Qwen3.6 35B A3B NVFP4
AI ModelThe Qwen3.6 35B A3B NVFP4 is a specialized iteration of the Qwen series, optimized specifically for NVIDIA har
AI Model · sentence-similarity
All (18)all-MiniLM-L6-v2
AI ModelFast sentence embeddings
paraphrase multilingual MiniLM L12 v2
AI ModelThe paraphrase-multilingual-MiniLM-L12-v2 is a lightweight, high-performance transformer model optimized for g
bge m3
AI ModelBGE-M3 is a versatile embedding model designed for high-performance retrieval across diverse linguistic landsc
all mpnet base v2
AI Modelall-mpnet-base-v2 is a high-performance sentence-transformer model optimized for mapping text to a dense vecto
nomic embed text v1.5
AI Modelnomic-embed-text-v1.5 is a high-performance text embedding model designed for scalable retrieval and semantic
multilingual e5 small
AI ModelMultilingual E5 Small is a lightweight, high-efficiency embedding model designed for cross-lingual sentence si
paraphrase multilingual mpnet base v2
AI ModelThe paraphrase-multilingual-mpnet-base-v2 is a robust sentence-embedding model designed for cross-lingual sema
multilingual e5 base
AI ModelMultilingual-e5-base is a high-performance text embedding model designed for cross-lingual semantic search and
AI Model · question-answering
All (18)electra large discriminator squad2 512
AI ModelThe ELECTRA-Large Discriminator, fine-tuned on SQuAD 2.0, is a specialized encoder model designed for high-pre
roberta base squad2
AI Modelroberta-base-squad2 is a robust extractive question-answering model based on the RoBERTa architecture, specifi
koelectra base v3 finetuned korquad
AI ModelThe koelectra-base-v3-korquad model is a specialized encoder-based transformer optimized for Korean extractive
distilbert base cased distilled squad
AI ModelDistilBERT-base-cased-distilled-SQuAD is a lightweight, transformer-based model optimized for extractive quest
bert large uncased whole word masking squad2
AI ModelThe BERT-Large-Uncased-WWM-SQuAD2 model is a specialized encoder designed for high-precision extractive questi
tinyroberta squad2
AI ModelTinyRoBERTa-SQuAD2 is a compact, distilled version of the RoBERTa architecture specifically fine-tuned for ext
koelectra small v2 distilled korquad 384
AI ModelKoELECTRA-Small v2 is a lightweight, distilled transformer model optimized specifically for Korean language un
xlm roberta base squad2
AI Modelxlm-roberta-base-squad2 is a cross-lingual transformer model fine-tuned specifically for extractive question a
AI Model · table-question-answering
All (18)tapex base finetuned wikisql
AI ModelTaPEX (Table Pre-training Experiment) is a specialized encoder-decoder model designed specifically for table-b
tapas large finetuned sqa
AI ModelThe TAPAS Large model, fine-tuned on the SQuAD-style table question answering (SQuA) dataset, is designed spec
tapas base finetuned wtq
AI ModelThe tapas-base-finetuned-wtq model is a specialized transformer architecture designed specifically for Table Q
tapas base finetuned sqa
AI ModelThe TAPAS Base model, fine-tuned on the SQuAD-style table questioning dataset, is designed specifically for ta
tapas large finetuned wtq
AI ModelThe TAPAS Large model, fine-tuned on the WikiTableQuestions (WtQ) dataset, is a specialized transformer design
tapas tiny finetuned sqa
AI ModelThe Tapas Tiny SQA model is a specialized transformer designed for Table Question Answering (TableQA). Unlike
tiny tapas random wtq
AI ModelTiny TAPAS (Random WTQ) is a specialized, lightweight model designed for table-based question answering. Unlik
tiny tapas random sqa
AI ModelTiny Tapas Random SQA is a lightweight, specialized model designed for table-based question answering. Unlike
AI Model · image-to-text
All (18)blip image captioning base
AI ModelBLIP (Bootstrapping Language-Image Pre-training) is a versatile vision-language model designed to bridge the g
PP OCRv5 server det
AI ModelPP OCRv5 server det is a high-performance text detection model designed for industrial-scale OCR pipelines. Un
manga ocr base
AI ModelManga OCR Base is a specialized image-to-text model engineered specifically for the complexities of Japanese m
blip image captioning large
AI ModelBLIP (Bootstrapping Language-Image Pre-training) Large is a versatile vision-language model designed for high-
en PP OCRv5 mobile rec
AI ModelThe PP-OCRv5 mobile recognition model is a lightweight, high-efficiency text recognition engine optimized for
UVDoc
AI ModelUVDoc is a specialized image-to-text model developed by PaddlePaddle, designed to handle complex document pars
trocr small handwritten
AI ModelTrOCR-small is a lightweight transformer-based model designed specifically for optical character recognition o
pix2text mfr
AI Modelpix2text mfr is a specialized image-to-text model designed for high-accuracy mathematical formula recognition.
AI Model · image-text-to-text
All (18)Qwen3.5 9B
AI ModelQwen3.5 9B is a versatile multimodal model designed to bridge the gap between lightweight efficiency and high-
Qwen3.6 35B A3B FP8
AI ModelQwen3.6 35B A3B FP8 is a multimodal model designed for efficient image-text processing. By utilizing FP8 quant
gemma 4 26B A4B it
AI ModelGemma 4 26B A4B is a multimodal model from Google, designed for developers needing high-performance image-to-t
gemma 4 31B it
AI ModelGemma 4 31B IT is a mid-sized, instruction-tuned multimodal model designed for developers who need a balance b
Qwen2.5 VL 7B Instruct
AI ModelQwen2.5 VL 7B Instruct is a versatile vision-language model designed for high-precision image and video unders
Qwen3.6 27B FP8
AI ModelQwen3.6 27B FP8 is a high-efficiency multimodal model designed for developers who need a balance between reaso
Qwen3.5 4B
AI ModelQwen3.5 4B is a compact multimodal model designed for efficient image-and-text processing. Unlike larger LLMs
Qwen2.5 VL 3B Instruct
AI ModelQwen2.5 VL 3B Instruct is a lightweight yet powerful vision-language model designed for efficient multimodal p
AI Model · object-detection
All (18)table transformer structure recognition
AI ModelTable Transformer (TATR) is a specialized object detection model designed to automate the structural analysis
table transformer detection
AI ModelTable Transformer (TATR) is a specialized object detection model designed to solve the complex problem of tabl
yolos small
AI ModelYOLOS-Small is a streamlined object detection model that replaces traditional convolutional backbones with a V
PP DocLayoutV3 safetensors
AI ModelPP DocLayoutV3 is a specialized object detection model optimized for document layout analysis. Unlike general-
rtdetr r101vd coco o365
AI ModelThe RT-DETR R101VD is a real-time end-to-end object detector that eliminates the need for non-maximum suppress
rtdetr v2 r18vd
AI ModelRT-DETR v2 (R18VD) is a high-performance real-time object detector that bridges the gap between the speed of Y
detr resnet 50
AI ModelDETR (Detection Transformer) with a ResNet-50 backbone represents a fundamental shift in object detection by r
table transformer structure recognition v1.1 all
AI ModelTable Transformer (TATR) v1.1 is a specialized object-detection model designed to automate the extraction of s
AI Model · summarization
All (17)BART Large CNN
AI ModelSummarization and text generation
distilbart cnn 12 6
AI ModelDistilBART-cnn-12-6 is a streamlined version of the BART architecture, specifically optimized for abstractive
pegasus xsum
AI ModelPegasus XSum is a specialized transformer model engineered specifically for extreme summarization. Unlike gene
financial summarization pegasus
AI ModelFinancial Summarization Pegasus is a domain-specific encoder-decoder model fine-tuned for the nuances of finan
bart large cnn samsum
AI ModelThe bart-large-cnn-samsum model is a specialized encoder-decoder transformer fine-tuned specifically for conve
distilbart xsum 12 6
AI ModelDistilBART-xsum-12-6 is a compressed version of the BART architecture specifically fine-tuned for extreme summ
text summarization
AI ModelThis model, hosted by Falconsai, is a specialized tool designed for efficient text summarization tasks. Unlike
MEETING SUMMARY
AI ModelThe MEETING SUMMARY model is a specialized tool designed for distilling lengthy meeting transcripts into conci
AI Model · text-classification
All (17)bge reranker v2 m3
AI ModelThe BGE Reranker v2 M3 is a cross-encoder model designed to refine the output of initial retrieval stages in R
finbert
AI ModelFinBERT is a domain-specific adaptation of the BERT architecture, pre-trained on a massive corpus of financial
Prompt Guard 86M
AI ModelPrompt Guard 86M is a lightweight, specialized classifier designed to secure LLM pipelines by detecting prompt
bge reranker base
AI ModelThe bge-reranker-base is a cross-encoder model designed to refine the results of initial vector searches. Unli
distilbert base uncased finetuned sst 2 english
AI ModelDistilBERT base uncased finetuned SST-2 is a lightweight, distilled version of BERT optimized for binary senti
twitter roberta base sentiment latest
AI ModelThe twitter-roberta-base-sentiment-latest model is a specialized text classifier fine-tuned on a massive corpu
koelectra small v3 nsmc
AI ModelKoELECTRA Small v3 (NSMC) is a lightweight, discriminative transformer model optimized for Korean sentiment an
tiny Qwen2ForSequenceClassification 2.5
AI ModelThe tiny Qwen2ForSequenceClassification 2.5 is a lightweight, encoder-style adaptation of the Qwen2 architectu
AI Model · token-classification
All (17)indonesian roberta base posp tagger
AI ModelThe indonesian-roberta-base-posp-tagger is a specialized token-classification model designed for Part-of-Speec
stanford deidentifier base
AI ModelThe Stanford Deidentifier Base is a specialized token-classification model designed to automate the removal of
bert base NER
AI ModelThe bert-base-NER model is a specialized token-classification transformer fine-tuned for Named Entity Recognit
bert large cased finetuned conll03 english
AI ModelThis model is a BERT-Large architecture specifically fine-tuned on the CoNLL-03 dataset for English Named Enti
punctuate all
AI ModelPunctuate All is a specialized token-classification model designed to automate punctuation restoration in unst
ner english fast
AI ModelThe 'ner-english-fast' model is a lightweight token-classification tool designed for high-throughput Named Ent
sat 3l sm
AI ModelThe sat 3l sm model is a specialized token-classification engine designed for precise text segmentation. Unlik
bert portuguese ner
AI ModelThe BERT Portuguese NER model is a specialized token-classification engine fine-tuned specifically for Named E
AI Model · fill-mask
All (17)bert base uncased
AI ModelBERT Base Uncased is a foundational transformer-based encoder designed for bidirectional representation learni
xlm roberta base
AI ModelXLM-RoBERTa Base is a multilingual transformer model designed for high-performance Natural Language Understand
roberta base
AI ModelRoBERTa-base is an optimized evolution of the BERT architecture, designed for developers who need high-perform
roberta large
AI ModelRoBERTa-large is a robustly optimized version of BERT, designed for developers who need high-performance natur
distilbert base uncased
AI ModelDistilBERT base uncased is a streamlined, lightweight version of the BERT architecture, designed for developer
xlm roberta large
AI ModelXLM-RoBERTa Large is a powerful multilingual transformer model designed for cross-lingual representation learn
ModernBERT base
AI ModelModernBERT is a complete architectural refresh of the BERT encoder, designed to bridge the gap between legacy
mdeberta v3 base
AI Modelmdeberta-v3-base is a refined encoder-only transformer that optimizes the DeBERTa architecture for superior pe
AI Model · feature-extraction
All (17)bge small en v1.5
AI ModelThe bge-small-en-v1.5 is a lightweight embedding model designed for high-efficiency vectorization of English t
bge large en v1.5
AI ModelThe bge-large-en-v1.5 is a high-performance embedding model designed for transforming text into dense vectors
bge base en v1.5
AI ModelThe bge-base-en-v1.5 is a high-performance embedding model designed for transforming text into dense vectors f
Qwen3 Embedding 0.6B
AI ModelQwen3 Embedding 0.6B is a compact, high-efficiency feature extraction model designed for developers building R
multilingual e5 large
AI ModelMultilingual E5 Large is a high-performance text embedding model designed for cross-lingual semantic search an
bge small zh v1.5
AI ModelThe bge-small-zh-v1.5 is a lightweight embedding model optimized for Chinese language tasks. Designed for effi
granite embedding small english r2
AI ModelThe granite-embedding-small-english-r2 is a lightweight, English-centric feature extraction model designed for
mxbai embed large v1
AI Modelmxbai-embed-large-v1 is a high-performance embedding model designed for developers building RAG pipelines and
AI Model · voice-activity-detection
All (17)segmentation 3.0
AI ModelSegmentation 3.0 by pyannote is a specialized voice activity detection (VAD) model designed to distinguish hum
segmentation
AI ModelThe pyannote segmentation model is a specialized tool for Voice Activity Detection (VAD) and speaker change de
Namo Turn Detector v1 Korean
AI ModelNamo Turn Detector v1 is a specialized Voice Activity Detection (VAD) model optimized specifically for the Kor
speaker diarization precision 2
AI ModelSpeaker Diarization Precision 2, powered by pyannote, is a specialized voice-activity-detection tool designed
Silero VAD v5 MLX
AI ModelSilero VAD v5 MLX is a specialized voice activity detection model optimized for Apple Silicon via the MLX fram
silero vad coreml
AI ModelSilero VAD CoreML is a specialized voice activity detection model optimized for Apple's hardware acceleration.
brouhaha
AI ModelBrouhaha is a specialized voice activity detection (VAD) model developed by pyannote, designed to distinguish
Pyannote Segmentation MLX
AI ModelPyannote Segmentation MLX is a specialized voice activity detection (VAD) and speaker segmentation model optim
AI Model · image-classification
All (17)mobilenetv3 small 100.lamb in1k
AI ModelMobileNetV3-Small is a lightweight convolutional neural network optimized for low-latency inference on mobile
vit base patch16 224
AI ModelThe ViT-B/16 is a foundational Vision Transformer that replaces traditional convolutional layers with a pure t
nsfw image detection
AI ModelThe nsfw image detection model by Falconsai is a specialized image classification tool designed to automate co
tf efficientnetv2 s.in21k ft in1k
AI ModelThe EfficientNetV2-S (in21k-ft-in1k) is a high-performance convolutional neural network optimized for image cl
fairface age image detection
AI ModelThe FairFace age detection model is a specialized image classification tool designed to mitigate demographic b
resnet50.a1 in1k
AI ModelThe resnet50.a1_in1k is a refined implementation of the classic ResNet-50 architecture, optimized for image cl
resnet18.a1 in1k
AI ModelThe resnet18.a1_in1k is a lightweight convolutional neural network based on the ResNet-18 architecture, pre-tr
resnet 50
AI ModelResNet-50 is a foundational deep residual network that solved the vanishing gradient problem in deep architect
AI Model · audio-generation
All (17)music generation model GGUF
AI ModelThis GGUF-quantized music generation model brings high-fidelity audio synthesis to local environments, elimina
distilgpt2 abc irish music generation
AI ModelThe distilgpt2-abc-irish-music model is a specialized generative tool designed for developers working with sym
music generation
AI ModelThis music generation model by DancingIguana offers an open-source alternative for integrating high-fidelity a
GPT2 Music Generation Trained
AI ModelThis model adapts the GPT-2 transformer architecture for symbolic music generation, treating musical notes and
music generation
AI ModelThis music generation model provides a lightweight, MIT-licensed solution for developers needing programmatic
music generation model
AI ModelThis audio generation model provides a flexible toolset for developers looking to integrate programmatic music
music generation
AI ModelThis music generation model provides a flexible, MIT-licensed solution for developers looking to integrate pro
Sinhala Audio to Text
AI ModelThe Sinhala Audio to Text model provides a specialized speech-to-text pipeline for the Sinhala language, addre
AI Model · translation
All (16)t5 small
AI ModelT5-Small is a lightweight, encoder-decoder transformer model designed for text-to-text tasks. Unlike decoder-o
t5 base
AI ModelT5 (Text-to-Text Transfer Transformer) Base is a versatile encoder-decoder model that treats every NLP task as
opus mt nl en
AI ModelThe opus-mt-nl-en model is a specialized neural machine translation (NMT) tool designed specifically for Dutch
opus mt fr en
AI ModelThe Opus MT FR-EN model is a specialized translation engine developed by Helsinki-NLP, designed specifically f
vntl llama3 8b v2 gguf
AI ModelThe vntl-llama3-8b-v2 is a specialized GGUF quantization of Meta's Llama 3 8B, fine-tuned specifically for hig
opus mt en ru
AI ModelOpus-MT EN-RU is a specialized neural machine translation model developed by Helsinki-NLP, designed specifical
opus mt en de
AI ModelThe opus-mt-en-de model is a specialized neural machine translation (NMT) tool developed by Helsinki-NLP, desi
opus mt de en
AI ModelThe opus-mt-de-en model is a specialized neural machine translation (NMT) engine developed by Helsinki-NLP, de
AI Model · visual-question-answering
All (16)blip vqa base
AI ModelBLIP-VQA Base is a vision-language model designed for visual question answering, bridging the gap between imag
vilt b32 finetuned vqa
AI ModelThe ViLT b32 finetuned VQA model is a streamlined vision-and-language transformer designed for Visual Question
MiniCPM V 2
AI ModelMiniCPM-V 2 is a compact yet powerful vision-language model designed to bridge the gap between edge-device eff
deplot
AI ModelDePlot is a specialized visual-question-answering (VQA) model designed to bridge the gap between plotted data
blip vqa capfilt large
AI ModelThe BLIP VQA Capfilt Large is a specialized vision-language model designed for precise visual question answeri
Qwen3.5 2B MedVL
AI ModelQwen3.5 2B MedVL is a compact vision-language model specifically tuned for the medical domain. Designed for ef
VideoScore2
AI ModelVideoScore2 is a specialized visual-question-answering (VQA) model designed to quantify video quality and sema
llava med v1.5 mistral 7b hf
AI ModelLLaVA-Med v1.5 Mistral 7B HF is a domain-specific multimodal model designed for biomedical visual question ans
AI Model · automatic-speech-recognition
All (16)whisperkit coreml
AI ModelWhisperKit CoreML brings OpenAI's Whisper speech-to-text capabilities directly to Apple silicon, optimizing in
speaker diarization 3.1
AI ModelSpeaker Diarization 3.1, powered by pyannote, is a specialized framework designed to solve the 'who spoke when
whisper large v3 turbo
AI ModelWhisper large-v3-turbo is a streamlined version of OpenAI's state-of-the-art speech recognition model, enginee
wav2vec2 large xlsr 53 japanese
AI ModelThe wav2vec2-large-xlsr-53-japanese model is a robust automatic speech recognition (ASR) tool fine-tuned for J
speaker diarization community 1
AI ModelSpeaker Diarization Community 1, powered by pyannote, is a specialized tool for the 'who spoke when' problem i
wav2vec2 large xlsr 53 portuguese
AI ModelThe wav2vec2-large-xlsr-53-portuguese model is a robust Automatic Speech Recognition (ASR) tool fine-tuned spe
voice activity detection
AI ModelPyannote's Voice Activity Detection (VAD) is a specialized tool designed to distinguish human speech from sile
Qwen3 ASR 1.7B
AI ModelQwen3 ASR 1.7B is a compact, efficient automatic speech recognition model designed for low-latency transcripti
AI Model · text-to-image
All (15)Stable Diffusion XL
AI ModelHigh-quality image generation
stable diffusion xl base 1.0
AI ModelStable Diffusion XL (SDXL) 1.0 represents a significant architectural leap over previous versions, moving to a
stable diffusion v1 5
AI ModelStable Diffusion v1.5 remains a foundational pillar for open-source generative AI, offering a versatile text-t
dreamshaper 7
AI ModelDreamShaper 7 is a refined Stable Diffusion checkpoint designed to bridge the gap between photorealism and dig
Z Image Turbo
AI ModelZ Image Turbo is a high-performance text-to-image model designed for developers who need a balance between gen
sd turbo
AI ModelSD Turbo is a distilled version of Stable Diffusion designed specifically for real-time image synthesis. Unlik
Realistic Vision V5.1 noVAE
AI ModelRealistic Vision V5.1 (noVAE) is a fine-tuned Stable Diffusion checkpoint optimized specifically for photoreal
stable diffusion v1 4
AI ModelStable Diffusion v1.4 is a latent diffusion model designed for high-efficiency text-to-image synthesis. Unlike
AI Model · image-to-image
All (14)Qwen Image Edit 2509
AI ModelQwen Image Edit 2509 is a specialized image-to-image model designed for precise visual manipulation. Unlike ge
FLUX.2 klein 4B
AI ModelFLUX.2 klein 4B is a streamlined image-to-image model designed for developers who need a balance between gener
Qwen Image Edit 2511 Lightning
AI ModelQwen Image Edit 2511 Lightning is a specialized image-to-image model designed for high-speed visual manipulati
Qwen Edit 2509 Multiple angles
AI ModelQwen Edit 2509 is a specialized image-to-image model designed for precise spatial and perspective manipulation
Qwen Image Edit 2511 GGUF
AI ModelQwen Image Edit 2511 GGUF is a specialized image-to-image model optimized for local deployment via the GGUF fo
Qwen Image Edit 2511
AI ModelQwen Image Edit 2511 is a specialized image-to-image model designed for precise visual modifications. Unlike g
FLUX.2 small decoder
AI ModelFLUX.2 small decoder is a streamlined image-to-image component designed for developers who need efficient late
FLUX.2 klein base 4B
AI ModelFLUX.2 klein base 4B is a compact, efficient image-to-image model designed for high-fidelity visual transforma
AI Model · audio-to-audio
All (14)bigvgan v2 22khz 80band 256x
AI ModelBigVGAN v2 is a high-fidelity neural vocoder designed for high-resolution audio synthesis. Operating at 22kHz
bigvgan v2 44khz 128band 512x
AI ModelBigVGAN v2 is a high-fidelity neural vocoder designed for professional-grade speech and audio synthesis. Opera
Qwen3 TTS Tokenizer 12Hz
AI ModelThe Qwen3 TTS Tokenizer 12Hz is a specialized audio-to-audio component designed to bridge the gap between raw
neucodec
AI ModelNeucodec is an open-source audio-to-audio model designed for high-fidelity neural audio compression and recons
TIGER DnR
AI ModelTIGER DnR is a specialized audio-to-audio model designed for high-fidelity denoising and restoration. Unlike g
bigvgan v2 24khz 100band 256x
AI ModelBigVGAN v2 is a high-fidelity neural vocoder designed for high-resolution audio synthesis. Unlike traditional
MP SENet DNS
AI ModelMP SENet DNS is a specialized audio-to-audio model designed for high-fidelity deep noise suppression. Unlike g
distill neucodec
AI ModelDistill NeuCodec is an efficient audio-to-audio model designed for high-fidelity signal processing and compres
AI Model · zero-shot-classification
All (13)bart large mnli
AI ModelBART-large-MNLI is a specialized encoder-decoder model fine-tuned on the Multi-Genre Natural Language Inferenc
distilbert base uncased mnli
AI ModelDistilBERT base uncased MNLI is a streamlined transformer model optimized for zero-shot text classification. B
mDeBERTa v3 base mnli xnli
AI ModelmDeBERTa v3 base mnli xnli is a multilingual encoder model optimized for zero-shot text classification. Built
DeBERTa v3 base mnli fever anli
AI ModelDeBERTa v3 base mnli fever anli is a specialized NLI (Natural Language Inference) model optimized for zero-sho
DeBERTa v3 large mnli fever anli ling wanli
AI ModelThis model is a specialized DeBERTa v3 large variant fine-tuned on a comprehensive suite of Natural Language I
deberta v3 base zeroshot v2.0
AI ModelDeBERTa-v3-base-zeroshot-v2.0 is a specialized encoder model optimized for zero-shot text classification. Unli
deberta v3 large zeroshot v2.0
AI ModelDeBERTa v3 Large Zero-Shot v2.0 is a specialized encoder model optimized for Natural Language Inference (NLI)
bge m3 zeroshot v2.0
AI ModelThe bge-m3-zeroshot-v2.0 is a specialized classification model designed for high-efficiency zero-shot tasks, e
AI Model · text-to-speech
All (13)Kokoro 82M
AI ModelKokoro 82M is a highly efficient, small-footprint text-to-speech model designed for developers who need high-q
Qwen3 TTS 12Hz 1.7B CustomVoice
AI ModelQwen3 TTS 12Hz 1.7B CustomVoice is a lightweight, high-efficiency text-to-speech model designed for low-latenc
chatterbox
AI ModelChatterbox is a lightweight, MIT-licensed text-to-speech (TTS) engine developed by ResembleAI, designed for de
Kokoro 82M v1.0 ONNX
AI ModelKokoro 82M v1.0 is a lightweight, high-efficiency text-to-speech model optimized for local deployment via the
Qwen3 TTS 12Hz 0.6B CustomVoice
AI ModelQwen3 TTS 12Hz 0.6B CustomVoice is a lightweight, high-efficiency text-to-speech model designed for low-latenc
OmniVoice
AI ModelOmniVoice is an open-source text-to-speech (TTS) engine designed for developers needing high-fidelity voice sy
VibeVoice Realtime 0.5B
AI ModelVibeVoice Realtime 0.5B is a lightweight, low-latency text-to-speech model designed for real-time applications
Qwen3 TTS GGUF
AI ModelQwen3 TTS GGUF brings high-fidelity text-to-speech capabilities to local environments via the GGUF format, sig
AI Model · depth-estimation
All (13)Depth Anything V2 Small hf
AI ModelDepth Anything V2 Small is a lightweight monocular depth estimation model designed for real-time spatial analy
DA3METRIC LARGE
AI ModelDA3METRIC LARGE is a specialized depth-estimation model designed to recover high-fidelity metric depth from si
dpt hybrid midas
AI ModelDPT Hybrid MIDAS is a depth-estimation model designed to bridge the gap between high-resolution spatial detail
depth anything large hf
AI ModelDepth Anything Large is a powerful monocular depth estimation model designed to extract high-resolution spatia
Distill Any Depth Large hf
AI ModelDistill Any Depth Large is a specialized depth-estimation model designed for high-fidelity spatial mapping fro
DA3MONO LARGE
AI ModelDA3MONO LARGE is a specialized depth-estimation model designed to extract high-fidelity monocular depth maps f
zoedepth nyu kitti
AI ModelZoeDepth is a zero-shot metric depth estimation model designed to bridge the gap between relative and absolute
DA3 LARGE 1.1
AI ModelDA3 Large 1.1 is a specialized depth-estimation model designed to extract high-fidelity spatial information fr
AI Model · video-classification
All (13)vjepa2 vitl fpc64 256
AI ModelV-JEPA (ViT-L/fpc64/256) is a self-supervised video representation model designed for efficient spatial-tempor
vjepa2 vitg fpc64 256
AI ModelV-JEPA (ViT-G FPC64 256) is a sophisticated video representation model designed for self-supervised learning.
xclip base patch32
AI Modelxclip base patch32 is a specialized vision-language model optimized for video classification tasks. Unlike sta
vivit b 16x2 kinetics400
AI ModelViViT-B/16x2 is a Video Vision Transformer designed specifically for high-accuracy video classification. Unlik
xclip base patch32 16 frames
AI ModelThe xclip-base-patch32 model is a specialized video classification tool designed to extend CLIP's visual-langu
vivit b 16x2
AI ModelViViT-B/16x2 is a Video Vision Transformer designed for efficient video classification by treating video clips
ms eff gcvit deepfake b0 kodf
AI ModelThe ms-eff-gcvit-deepfake-b0 is a specialized video classification model designed to detect synthetic media an
ms eff gcvit deepfake b5 kodf
AI ModelThe ms-eff-gcvit-deepfake-b5-kodf is a specialized video classification model designed for high-accuracy deepf
AI Model · document-question-answering
All (12)layoutlm document qa
AI ModelLayoutLM is a specialized transformer model designed for Document AI, bridging the gap between raw text and vi
donut base finetuned docvqa
AI ModelThe Donut-base model finetuned for DocVQA represents a shift toward OCR-free document understanding. Unlike tr
tiny doc qa vision encoder decoder
AI ModelThe tiny-doc-qa-vision-encoder-decoder is a lightweight, specialized model designed for efficient document que
donut base finetuned docvqa
AI ModelThe Donut-based DocVQA model is an OCR-free transformer designed for document visual question answering. Unlik
layoutlmv2 base uncased finetuned docvqa
AI ModelLayoutLMv2-base-uncased-finetuned-docvqa is a multimodal transformer designed for Document Visual Question Ans
Llama 3.1 PersianQA
AI ModelLlama 3.1 PersianQA is a specialized adaptation of the Llama 3.1 architecture, fine-tuned specifically for doc
layoutlmv3 docvqa t11c5000
AI ModelLayoutLMv3 is a multimodal transformer designed for Document Visual Question Answering (DocVQA). Unlike tradit
bart qg finetune squad
AI ModelThe bart-qg-finetune-squad model is a specialized encoder-decoder architecture optimized for question generati
AI Model · image-feature-extraction
All (11)dinov2 small
AI ModelDINOv2-Small is a lightweight, self-supervised vision transformer designed for high-performance image feature
dinov2 base
AI ModelDINOv2 Base is a self-supervised vision transformer designed for high-performance image feature extraction wit
vit small patch14 dinov2.lvd142m
AI ModelThe ViT-Small Patch14 (DINOv2) is a lightweight vision transformer pre-trained on a massive, curated dataset o
dinov2 large
AI ModelDINOv2 Large is a self-supervised vision transformer designed for high-performance image feature extraction wi
vit base patch16 224 in21k
AI ModelThe ViT-Base-Patch16-224 (in21k) is a Vision Transformer pre-trained on the massive ImageNet-21k dataset. Unli
dino vitb16
AI ModelDINO ViT-B/16 is a self-supervised vision transformer designed for high-performance image feature extraction.
vit base patch14 dinov2.lvd142m
AI ModelThe ViT-Base Patch14 DINOv2 model is a high-performance vision transformer trained via self-supervised learnin
vit large patch14 reg4 dinov2.lvd142m
AI ModelThe ViT-L/14 DINOv2 model is a high-capacity vision transformer trained via self-supervised learning on a mass
AI Model · text2text-generation
All (11)flan t5 base
AI ModelFlan-T5 Base is an instruction-tuned version of the original T5 encoder-decoder framework, designed for develo
chronos t5 base
AI ModelChronos-T5 Base is a specialized time-series forecasting model that treats numerical sequences as language. By
chronos t5 tiny
AI ModelChronos-T5 Tiny is a lightweight, text-to-text model based on the T5 architecture, optimized for efficiency an
parrot paraphraser on T5
AI ModelThe Parrot Paraphraser is a specialized text-to-text model built on the T5 architecture, designed specifically
prot t5 xl uniref50
AI ModelProtT5-XL-UniRef50 is a specialized encoder-decoder transformer trained on the UniRef50 protein database, desi
chronos t5 small
AI ModelChronos-T5 Small is a specialized time-series forecasting model based on the T5 architecture, treating numeric
unifiedqa t5 small
AI ModelUnifiedQA T5-Small is a lightweight text-to-text model fine-tuned for a broad spectrum of question-answering t
flan t5 small
AI ModelFlan-T5 Small is a lightweight, encoder-decoder model designed for efficient text-to-text generation. Unlike t
AI Model · code-generation
All (10)DeepSeek Coder 33B
AI ModelCode generation and understanding
SWE BENCH generation claude reasoning llm correct swe gym 1500 plus critic qwen code 14b
AI ModelThis specialized model is engineered for high-autonomy software engineering tasks, specifically optimized for
Code Generation LLM LoRA Combined Model
AI ModelThe Code Generation LLM LoRA Combined Model is a specialized adapter-based solution designed to enhance standa
falcon rw 1b code generation llm task2 modelC
AI ModelFalcon RW 1B is a lightweight, specialized small language model (SLM) optimized for code generation tasks. Des
falcon code generation llm
AI ModelFalcon Code is a specialized LLM optimized for software engineering tasks, designed to bridge the gap between
falcon rw 1b code generation llm task2
AI ModelFalcon RW 1B is a compact, code-centric language model designed for efficient deployment in resource-constrain
Code Generation LLM LoRA
AI ModelThis LoRA adapter is specifically tuned for code generation tasks, designed to be layered atop a base LLM to e
falcon code generation task llm
AI ModelFalcon Code is a specialized LLM optimized for programmatic tasks, designed to bridge the gap between general-
AI Model · natural-language-inference
All (10)mDeBERTa v3 base xnli multilingual nli 2mil7
AI ModelmDeBERTa-v3-base-xnli is a specialized multilingual model optimized for Natural Language Inference (NLI). Base
nli mpnet base v2
AI ModelThe nli-mpnet-base-v2 is a robust sentence-transformer model optimized for generating high-quality semantic em
nli deberta v3 small
AI ModelThe NLI DeBERTa-v3-small is a lightweight cross-encoder optimized for Natural Language Inference (NLI). Unlike
bert base turkish cased mean nli stsb tr
AI ModelThis model is a specialized BERT-base variant fine-tuned for Turkish Natural Language Inference (NLI) and Sema
nli deberta v3 base
AI ModelThe NLI DeBERTa-v3-base is a high-performance cross-encoder optimized for Natural Language Inference tasks. Un
bert base nli mean tokens
AI ModelThe bert-base-nli-mean-tokens model is a specialized encoder designed to transform text into dense vector embe
nli MiniLM2 L6 H768
AI ModelThe nli MiniLM2 L6 H768 is a lightweight cross-encoder optimized for Natural Language Inference (NLI) tasks. U
nli deberta v3 xsmall
AI ModelThe NLI DeBERTa-v3-xsmall is a compact cross-encoder optimized for Natural Language Inference (NLI) tasks. Unl
AI Model · audio-classification
All (10)clap htsat fused
AI ModelCLAP HTSAT Fused is a specialized audio representation model designed for high-accuracy audio classification a
ast finetuned audioset 10 10 0.4593
AI ModelThis model is a fine-tuned implementation of the Audio Spectrogram Transformer (AST), specifically optimized f
wav2vec2 large xlsr 53 gender recognition librispeech
AI ModelThis model is a specialized fine-tuned version of Meta's wav2vec2-large-xlsr-53, optimized specifically for ge
ced gguf
AI ModelThe ced gguf model is a specialized audio classification tool optimized for local deployment via the GGUF form
audiobox aesthetics
AI ModelAudiobox Aesthetics is a specialized audio classification model from Meta designed to quantify the subjective
gender cls svm ecapa voxceleb
AI ModelThis model is a specialized gender classification tool leveraging ECAPA-TDNN embeddings trained on the VoxCele
voice gender classifier
AI ModelThe Voice Gender Classifier is a specialized audio classification model designed to determine the perceived ge
hubert large speech emotion recognition russian dusha finetuned
AI ModelThe hubert-large-speech-emotion-recognition-russian-dusha is a specialized audio classification model fine-tun
AI Model · image-text-retrieval
All (10)clip vit base patch32
AI ModelCLIP ViT-B/32 is a versatile vision-language model designed for zero-shot image and text understanding. Unlike
clip vit large patch14
AI ModelCLIP ViT-L/14 is a powerful vision-language model designed for zero-shot image and text understanding. Unlike
clip vit large patch14 336
AI ModelCLIP ViT-L/14@336 is a high-resolution vision-language model designed for precise image-text alignment. By uti
CLIP ViT B 32 laion2B s34B b79K
AI ModelCLIP ViT-B/32 (trained on LAION-2B) is a robust vision-language model designed for high-performance image-text
fashion clip
AI ModelFashion CLIP is a domain-specific adaptation of the CLIP architecture, fine-tuned specifically for the fashion
CLIP convnext base w laion2B s13B b82K augreg
AI ModelThis model is a high-performance vision-language encoder based on the ConvNeXt architecture, trained on the ma
clip vit base patch16
AI ModelCLIP ViT-B/16 is a versatile vision-language model designed to map images and text into a shared embedding spa
tiny clip text 2
AI ModelTiny CLIP Text 2 is a lightweight image-text retrieval model designed for developers who need efficient embedd
AI Model · image-generation
All (9)NL Diffusion Image GGUF
AI ModelNL Diffusion Image GGUF brings high-quality image synthesis to local environments by leveraging the GGUF quant
diffusion models image
AI ModelThis diffusion-based image generation model provides a flexible, open-source solution for developers needing h
diffusion models image
AI ModelThis image generation model leverages a diffusion-based architecture to transform text prompts into high-fidel
stable diffusion trained on yujiro hanma images baki anime fun project
AI ModelThis specialized Stable Diffusion checkpoint is fine-tuned on a targeted dataset of Yujiro Hanma from the Baki
blip image2promt stable diffusion base
AI ModelThe BLIP image2prompt model is a specialized vision-language tool designed to reverse-engineer text prompts fr
Medical X ray image generation stable diffusion
AI ModelThis Stable Diffusion fine-tune is engineered specifically for synthesizing medical X-ray imagery, bridging th
stable diffusion finetuned
AI ModelThis fine-tuned iteration of Stable Diffusion is designed for developers needing higher precision and stylisti
stable diffusion base 2.0 text to image 04
AI ModelStable Diffusion v2.0 is a latent diffusion model designed for high-fidelity text-to-image synthesis. Unlike i
AI Model · text-to-audio
All (8)Ace Step1.5
AI ModelAce Step1.5 is a streamlined text-to-audio model designed for developers needing efficient, high-fidelity spee
Ace Step1.5 XL DF11 ComfyUI
AI ModelAce Step1.5 XL DF11 is a specialized text-to-audio model optimized for the ComfyUI ecosystem. Unlike general-p
fastspeech2 conformer
AI ModelFastSpeech 2 Conformer is a non-autoregressive text-to-speech (TTS) model designed for high-fidelity audio syn
acestep 5Hz lm 4B
AI ModelThe acestep 5Hz lm 4B is a lightweight, open-source text-to-audio model designed for low-latency synthesis. Wi
fastspeech2 conformer with hifigan
AI ModelThis model combines the FastSpeech 2 architecture with Conformer blocks and a HiFi-GAN vocoder to deliver high
MiniMax Music3
AI ModelMiniMax Music3 is a specialized text-to-audio model designed for high-fidelity music generation. For developer
acestep 5Hz lm 0.6B
AI ModelThe acestep 5Hz lm 0.6B is a lightweight, text-to-audio model designed for low-latency synthesis. At 0.6B para
acestep v15 xl sft
AI Modelacestep v15 xl sft is a specialized text-to-audio model designed for high-fidelity sound synthesis. Unlike gen
AI Model · image-to-video
All (7)Wan2.2 I2V A14B GGUF
AI ModelWan2.2 I2V A14B GGUF is a quantized image-to-video generation model designed for developers seeking high-fidel
Minimax h3 Turbo
AI ModelMinimax h3 Turbo is a specialized image-to-video generation model designed for developers needing high-fidelit
Wan2.2 Distill Loras
AI ModelWan2.2 Distill LoRAs are specialized adapters designed to optimize image-to-video generation by leveraging kno
LTX2.3 10Eros
AI ModelLTX2.3 10Eros is a specialized image-to-video generation model designed for developers building dynamic visual
Wan2.2 I2V A14B Diffusers
AI ModelWan2.2 I2V A14B is a high-capacity image-to-video diffusion model designed for developers requiring cinematic
MiniMax H3 encoder GGUF
AI ModelThe MiniMax H3 encoder, now available in GGUF format, provides a quantized implementation of the vision encodi
Wan2.1 I2V 14B 480P gguf
AI ModelWan2.1 I2V 14B 480P is a specialized image-to-video diffusion model optimized for developers seeking a balance
AI Model · image-segmentation
All (7)clipseg rd64 refined
AI ModelClipSeg RD64 Refined is a specialized image segmentation model designed for zero-shot performance, leveraging
BiRefNet
AI ModelBiRefNet is a high-performance image segmentation model specifically engineered for precise binary reference-b
segformer b0 finetuned ade 512 512
AI ModelSegFormer-B0 (finetuned on ADE20K) is a lightweight, hierarchical Transformer-based model designed for efficie
face parsing
AI ModelThis face parsing model provides high-precision semantic segmentation of human facial features, mapping specif
oneformer cityscapes swin large
AI ModelOneFormer Cityscapes Swin-Large is a high-performance image segmentation model designed for precise semantic,
coco panoptic eomt large 640
AI ModelThe coco panoptic eomt large 640 is a specialized image segmentation model designed for high-precision panopti
modnet
AI ModelModNet is a lightweight, real-time portrait matting model designed for high-fidelity alpha matte estimation. U
AI Model · ocr
All (6)chandra ocr 2
AI ModelChandra OCR 2 is a specialized vision-language model optimized for high-accuracy text extraction and document
DeepSeek OCR
AI ModelDeepSeek OCR is a specialized vision-language model designed to bridge the gap between raw image pixels and st
surya ocr 2
AI ModelSurya OCR 2 is a high-performance vision-language model designed for precise document analysis and text extrac
DeepSeek OCR 2
AI ModelDeepSeek OCR 2 is a specialized vision-language model engineered to bridge the gap between raw image data and
Unlimited OCR AWQ
AI ModelUnlimited OCR AWQ is a specialized vision-language model optimized for high-accuracy optical character recogni
GOT OCR2 0
AI ModelGOT OCR2.0 is a specialized vision-language model designed to bridge the gap between raw image data and struct
AI Model · sentiment-analysis
All (4)sentiment analysis fine tuned model
AI ModelThis fine-tuned sentiment analysis model is designed for developers needing a lightweight, specialized tool fo
twitter roberta base sentiment
AI ModelThe twitter-roberta-base-sentiment model is a specialized encoder based on the RoBERTa architecture, fine-tune
Bangla twoclass Sentiment Analyzer
AI ModelThe Bangla Two-Class Sentiment Analyzer is a specialized NLP model designed for binary sentiment classificatio
rubert base cased sentiment rusentiment
AI ModelRuBERT-base-cased-sentiment (RuSentiment) is a specialized transformer model optimized for sentiment analysis
AI Model · multimodal-representation
All (4)ChestVision Fine Tuned Vision Language Model
AI ModelChestVision is a specialized Vision Language Model (VLM) fine-tuned specifically for medical imaging, focusing
Touch Vision Language Models
AI ModelTouch Vision Language Models (TVLMs) extend traditional multimodal architectures by integrating tactile sensin
vision language garment model
AI ModelThe Vision Language Garment model is a specialized multimodal representation tool designed to bridge the gap b
vision language model
AI ModelThis Vision Language Model (VLM) is a multimodal architecture designed to bridge the gap between visual percep
AI Model · image-quality-assessment
All (3)generated image quality assessment
AI ModelThis model provides a specialized solution for evaluating the fidelity and visual quality of synthetic images.
face image quality assessment ediffiqa
AI ModelEdiffiQA is a specialized image quality assessment (IQA) model integrated within the OpenCV ecosystem, designe
AAL Plus Image Quality Assessment
AI ModelAAL Plus is a specialized Image Quality Assessment (IQA) model designed to provide objective, quantitative met
AI Model · text generation
All (3)GPT-4
AI ModelMost capable GPT model for complex tasks
Claude 3.5 Sonnet
AI ModelAdvanced AI assistant with superior reasoning
Gemini 1.5 Pro
AI ModelMultimodal AI with long context
AI Model · audio
All (1)Whisper Large V3
AI ModelRobust speech recognition model
AI Skill · General
All (366)Job Interviewer
AI SkillI want you to act as an interviewer. I will be the candidate and you will ask me the interview questions for t
Travel Guide
AI SkillI want you to act as a travel guide. I will write you my location and you will suggest a place to visit near m
Plagiarism Checker
AI SkillI want you to act as a plagiarism checker. I will write you sentences and you will only reply undetected in pl
Character
AI SkillI want you to act like {character} from {series}. I want you to respond and answer like {character} using the
Advertiser
AI SkillI want you to act as an advertiser. You will create a campaign to promote a product or service of your choice.
Storyteller
AI SkillI want you to act as a storyteller. You will come up with entertaining stories that are engaging, imaginative
Football Commentator
AI SkillI want you to act as a football commentator. I will give you descriptions of football matches in progress and
Stand-up Comedian
AI SkillI want you to act as a stand-up comedian. I will provide you with some topics related to current events and yo
AI Skill · Coding
All (284)Code Reviewer
AI SkillReview code for bugs, security issues, and best practices
Ethereum Developer
AI SkillImagine you are an experienced Ethereum developer tasked with creating a smart contract for a blockchain messe
Linux Terminal
AI SkillI want you to act as a linux terminal. I will type commands and you will reply with what the terminal should s
JavaScript Console
AI SkillI want you to act as a javascript console. I will type commands and you will reply with what the javascript co
Excel Sheet
AI SkillI want you to act as a text based excel. you'll only reply me the text-based 10 rows excel sheet with row numb
UX/UI Developer
AI SkillI want you to act as a UX/UI developer. I will provide some details about the design of an app, website or oth
Cyber Security Specialist
AI SkillI want you to act as a cyber security specialist. I will provide some specific information about how data is s
Web Design Consultant
AI SkillI want you to act as a web design consultant. I will provide you with details related to an organization needi
AI Skill · Data
All (53)ad-campaign-analyzer
AI SkillAnalyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without o
alpha-vantage
AI SkillAccess 20+ years of global financial data: equities, options, forex, crypto, commodities, economic indicators,
analytics-tracking
AI SkillSet up, audit, and debug analytics tracking implementation — GA4, Google Tag Manager, event taxonomy, conversi
angular-ui-patterns
AI SkillModern Angular UI patterns for loading states, error handling, and data display. Use when building UI componen
anti-reversing-techniques
AI SkillAUTHORIZED USE ONLY: This skill contains dual-use security techniques. Before proceeding with any bypass or an
apify-audience-analysis
AI SkillUnderstand audience demographics, preferences, behavior patterns, and engagement quality across Facebook, Inst
apify-ecommerce
AI SkillExtract product data, prices, reviews, and seller information from any e-commerce platform using Apify's E-com
apify-market-research
AI SkillAnalyze market conditions, geographic opportunities, pricing, consumer behavior, and product validation across
AI Skill · Business
All (41)Marketing Expert
AI SkillCreate marketing strategies and ad copy
Recruiter
AI SkillI want you to act as a recruiter. I will provide some information about job openings, and it will be your job
Startup Idea Generator
AI SkillGenerate digital startup ideas based on the wish of the people. For example, when I say "I wish there's a big
Salesperson
AI SkillI want you to act as a salesperson. Try to market something to me, but make what you're trying to market look
Startup Tech Lawyer
AI SkillI will ask of you to prepare a 1 page draft of a design partner agreement between a tech startup with IP and a
Product Manager
AI SkillPlease acknowledge my following request. Please respond to me as a product manager. I will ask for subject, an
internal-comms
AI SkillUse when a Head of People Ops, BizOps lead, or Internal Communications owner needs to draft and sequence an in
slack-gif-creator
AI SkillKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools
AI Skill · Design
All (41)Prompt Generator
AI SkillI want you to act as a prompt generator. Firstly, I will give you a title like this: "Act as an English Pronun
Digital Art Gallery Guide
AI SkillI want you to act as a digital art gallery guide. You will be responsible for curating virtual exhibits, resea
Midjourney Prompt Generator
AI SkillI want you to act as a prompt generator for Midjourney's artificial intelligence program. Your job is to provi
ChatGPT Prompt Generator
AI SkillI want you to act as a ChatGPT prompt generator, I will send a topic, you have to generate a ChatGPT prompt ba
brand-guidelines
AI SkillWhen the user wants to apply, document, or enforce brand guidelines for any product or company. Also use when
canvas-design
AI SkillCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when
frontend-design
AI SkillGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps w
theme-factory
AI SkillToolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing page
AI Skill · Writing
All (30)Screenwriter
AI SkillI want you to act as a screenwriter. You will develop an engaging and creative script for either a feature len
Poet
AI SkillI want you to act as a poet. You will create poems that evoke emotions and have the power to stir people's sou
Essay Writer
AI SkillI want you to act as an essay writer. You will need to research a given topic, formulate a thesis statement, a
Journalist
AI SkillI want you to act as a journalist. You will report on breaking news, write feature stories and opinion pieces,
doc-coauthoring
AI SkillGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documen
docx
AI SkillUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Wo
adhx
AI SkillFetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into struc
article-illustrations
AI SkillGenerate hand-drawn 16:9 article illustrations with the Grav character IP, sparse annotations, and absurd but
AI Skill · Office
All (10)Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text
pptx
AI SkillUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This include
xlsx
AI SkillUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user
azure-ai-translation-document-py
AI SkillAzure AI Document Translation SDK for batch translation of documents with format preservation. Use for transla
board-prep
AI SkillBoard meeting preparation for the adversarial scenario, not the friendly one. Forces numbers-cold mastery, ant
contract-and-proposal-writer
AI SkillGenerate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, ND
demo-video
AI SkillUse when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, m
md-slides
AI SkillConverts a markdown deck (slides separated by `---` HR boundaries or by `# ` H1 headings, with optional `<!--
AI Skill · Education
All (8)Motivational Coach
AI SkillI want you to act as a motivational coach. I will provide you with some information about someone's goals and
Debate Coach
AI SkillI want you to act as a debate coach. I will provide you with a team of debaters and the motion for their upcom
Relationship Coach
AI SkillI want you to act as a relationship coach. I will provide some details about the two people involved in a conf
AI Writing Tutor
AI SkillI want you to act as an AI writing tutor. I will provide you with a student who needs help improving their wri
Life Coach
AI SkillI want you to act as a life coach. I will provide some details about my current situation and goals, and it wi
Instructor in a School
AI SkillI want you to act as an instructor in a school, teaching algorithms to beginners. You will provide code exampl
Public Speaking Coach
AI SkillI want you to act as a public speaking coach. You will develop clear communication strategies, provide profess
Talent Coach
AI SkillI want you to act as a Talent Coach for interviews. I will give you a job title and you'll suggest what should
AI Skill · Translation
All (6)English Translator and Improver
AI SkillI want you to act as an English translator, spelling corrector and improver. I will speak to you in any langua
English Pronunciation Helper
AI SkillI want you to act as an English pronunciation assistant for ${Mother Language:Turkish} speaking people. I will
Spoken English Teacher and Improver
AI SkillI want you to act as a spoken English teacher and improver. I will speak to you in English and you will reply
New Language Creator
AI SkillI want you to translate the sentences I wrote into a new made up language. I will write the sentence, and you
Language Detector
AI SkillI want you act as a language detector. I will type a sentence in any language and you will answer me in which
Speech-Language Pathologist (SLP)
AI SkillI want you to act as a speech-language pathologist (SLP) and come up with new speech patterns, communication s
AI Skill · Marketing
All (1)SEO Optimizer
AI SkillOptimize content for search engines
MCP Tool · General
All (29)jdubois/azure-cli-mcp
MCP ToolA wrapper around the Azure CLI command line that allows you to talk directly to Azure
nwiizo/tfmcp
MCP Tool🦀 🏠 - A Terraform MCP server allowing AI assistants to manage and operate Terraform environments, enabling r
automateyournetwork/pyATS_MCP
MCP ToolCisco pyATS server enabling structured, model-driven interaction with network devices.
maxim-saplin/mcp_safe_local_python_executor
MCP ToolSafe Python interpreter based on HF Smolagents `LocalPythonExecutor`
sonirico/mcp-shell
MCP Tool🏎️ 🏠 🍎 🪟 🐧 Give hands to AI. MCP server to run shell commands securely, auditably, and on demand on isola
tumf/mcp-shell-server
MCP ToolA secure shell command execution server implementing the Model Context Protocol (MCP)
areweai/tsgram-mcp
MCP ToolTSgram: Telegram + Claude with local workspace access on your phone in typescript. Read, write, and vibe code
teddyzxcv/ntfy-mcp
MCP ToolThe MCP server that keeps you informed by sending the notification on phone using ntfy
MCP Tool · Web
All (16)thinkchainai/mcpbundles
MCP ToolMCP Bundles: Create custom bundles of tools and connect providers with OAuth or API keys. Use one MCP server a
microsoft/playwright-mcp
MCP ToolOfficial Microsoft Playwright MCP server, enabling LLMs to interact with web pages through structured accessib
hashicorp/terraform-mcp-server
MCP Tool🎖️🏎️☁️ - The official Terraform MCP Server seamlessly integrates with the Terraform ecosystem, enabling prov
sawa-zen/vrchat-mcp
MCP Tool📇 🏠 This is an MCP server for interacting with the VRChat API. You can retrieve information about friends, w
saurabhsharma2u/search-console-mcp
MCP ToolAn MCP server to interact with Google Search Console and Bing Webmasters.
OpenZeppelin/contracts-wizard
MCP ToolA Model Context Protocol (MCP) server that allows AI agents to generate secure smart contracts in multiples la
apiarya/wemo-mcp-server
MCP Tool[](https:
hbg/mcp-paperswithcode
MCP Tool🐍 ☁️ MCP to search through PapersWithCode API
MCP Tool · Database
All (11)mindsdb/mindsdb
MCP ToolConnect and unify data across various platforms and databases with [MindsDB as a single MCP server](https://do
Aiven-Open/mcp-aiven
MCP Tool🐍 ☁️ 🎖️ - Navigate your [Aiven projects](https://go.aiven.io/mcp-server) and interact with the PostgreSQL®,
alexanderzuev/supabase-mcp-server
MCP ToolSupabase MCP Server with support for SQL query execution and database exploration tools
bram2w/baserow
MCP ToolBaserow database integration with table search, list, and row create, read, update, and delete capabilities.
planetscale/mcp
MCP ToolThe PlanetScale CLI includes an MCP server that provides AI tools direct access to your PlanetScale databases.
longportapp/openapi
MCP Tool🐍 ☁️ - LongPort OpenAPI provides real-time stock market data, provides AI access analysis and trading capabil
traceloop/opentelemetry-mcp-server
MCP Tool🐍🏠 - An MCP server for connecting to any OpenTelemetry backend (Datadog, Grafana, Dynatrace, Traceloop, etc.
thinkchainai/agentinterviews_mcp
MCP ToolConduct AI-powered qualitative research interviews and surveys at scale with [Agent Interviews](https://agenti
MCP Tool · File System
All (6)finmap-org/mcp-server
MCP Tool[finmap.org](https://finmap.org/) MCP server provides comprehensive historical data from the US, UK, Russian a
urlbox/urlbox-mcp-server
MCP Tool📇 🏠 A reliable MCP server for generating and managing screenshots, PDFs, and videos, performing AI-powered s
Azure/azure-mcp
MCP ToolOfficial Microsoft MCP server for Azure services including Storage, Cosmos DB, and Azure Monitor.
mediar-ai/screenpipe
MCP Tool🎖️ 🦀 🏠 🍎 Local-first system capturing screen/audio with timestamped indexing, SQL/embedding storage, seman
MonadsAG/capsulecrm-mcp
MCP Tool📇 ☁️ Allows AI clients to manage contacts, opportunities and tasks in Capsule CRM including Claude Desktop re
MCP Filesystem
MCP ToolSecure file system access for Claude
MCP Tool · Search
All (3)andybrandt/mcp-simple-arxiv
MCP Tool🐍 ☁️ MCP for LLM to search and read papers from arXiv
andybrandt/mcp-simple-pubmed
MCP Tool🐍 ☁️ MCP to search and read medical / life sciences papers from PubMed.
tan-yong-sheng/ai-vision-mcp
MCP Tool📇 🏠 🍎 🪟 🐧 - Multimodal AI vision MCP server for image, video, and object detection analysis. Enables UI/U
MCP Tool · Development
All (1)TamarEngel/jira-github-mcp
MCP ToolMCP server that integrates Jira and GitHub to automate end-to-end developer workflows, from issue tracking to