Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
all-in-rag
AI repositories🔍大模型应用开发实战一:RAG 技术全栈指南,在线阅读地址:https://datawhalechina.github.io/all-in-rag/
git clone https://github.com/datawhalechina/all-in-rag.git -
bili-cli
Skills为 AI Agent 设计的哔哩哔哩命令行工具:扫码登录、看视频、评论、私信、发动态、投稿,全部 JSON 输出
git clone https://github.com/kukemc/bili-cli.git -
Unlimited-OCR
Modelsimage text to text model by baidu · transformers
baidu/Unlimited-OCR -
DeepSeek-V4.1-Flash
Modelsimage text to text model by deepseek-ai · transformers
deepseek-ai/DeepSeek-V4.1-Flash -
vectordb-recipes
AI repositoriesResource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs
git clone https://github.com/lancedb/vectordb-recipes.git -
OmniParser
Modelsimage text to text model by microsoft · transformers
microsoft/OmniParser -
JEV-35B-NVFP4
Modelstext classification model by autotrust · transformers
autotrust/JEV-35B-NVFP4 -
LemonDecider
Modelsfeature extraction model by inclusionAI · transformers
inclusionAI/LemonDecider -
Qwen2.5-Omni-7B
Modelsany to any model by Qwen · transformers
Qwen/Qwen2.5-Omni-7B -
OSWorld
Datasets & benchmarks[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
git clone https://github.com/xlang-ai/OSWorld.git -
OmniVLM-968M
Modelsmodel by NexaAI
NexaAI/OmniVLM-968M -
Florence-2-large
Modelsimage text to text model by microsoft · transformers
microsoft/Florence-2-large -
anything-llm
AI repositoriesStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
git clone https://github.com/Mintplex-Labs/anything-llm.git -
Octen-WebGR-4B
Modelstext generation model by Octen · transformers
Octen/Octen-WebGR-4B -
GLM-5.3-Flash
Modelsimage text to text model by zai-org · transformers
zai-org/GLM-5.3-Flash -
Muse-Glimmer-30B
Modelsimage text to text model by meta-models · transformers
meta-models/Muse-Glimmer-30B -
embeddinggemma-2-GGUF
Modelsfeature extraction model by unsloth
unsloth/embeddinggemma-2-GGUF -
fuyu-8b
Modelsimage text to text model by adept · transformers
adept/fuyu-8b -
Awesome-Multimodal-Prompts
PromptsPrompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3 Prompts.
git clone https://github.com/langgptai/Awesome-Multimodal-Prompts.git -
gemma-4-E4B-it
Modelsany to any model by google · transformers
google/gemma-4-E4B-it -
pplx-embed-v2-late-0.6b
Modelsfeature extraction model by perplexity-ai · sentence-transformers
perplexity-ai/pplx-embed-v2-late-0.6b -
janas
AI repositories37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
git clone https://github.com/prabanta-dev/janas.git -
Kimi-K2.5
Modelsimage text to text model by moonshotai · transformers
moonshotai/Kimi-K2.5 -
gemma-4-26B-A4B-it
Modelsimage text to text model by google · transformers
google/gemma-4-26B-A4B-it
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.