Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
LFM3-1.7B
Modelstext generation model by LiquidAI · transformers
LiquidAI/LFM3-1.7B -
Mamba-Codestral-7B-v0.1
Modelsmodel by mistralai · vllm
mistralai/Mamba-Codestral-7B-v0.1 -
haystack
Agents & frameworksOpen-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
git clone https://github.com/deepset-ai/haystack.git -
HunyuanImage-3.0
Modelstext to image model by tencent · transformers
tencent/HunyuanImage-3.0 -
CulturaX
Datasets & benchmarksHugging Face dataset by uonlp
uonlp/CulturaX -
MiniCPM-V-4.7-35B-A3B-gguf
Modelsimage text to text model by openbmb · llama.cpp
openbmb/MiniCPM-V-4.7-35B-A3B-gguf -
Cradle
AI repositoriesThe Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.
git clone https://github.com/BAAI-Agents/Cradle.git -
KG_RAG
PromptsEmpower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
git clone https://github.com/BaranziniLab/KG_RAG.git -
OmniVLM-968M
Modelsmodel by NexaAI
NexaAI/OmniVLM-968M -
c4
Datasets & benchmarksHugging Face dataset by allenai
allenai/c4 -
partmode
MCP serversOpen-source, local-first 3D parametric CAD that runs in the browser for people and permissioned typed agents, powered by OpenCascade WASM.
git clone https://github.com/BOMWiki/partmode.git -
DeepSeek-R1-GGUF
Modelstext generation model by unsloth · transformers
unsloth/DeepSeek-R1-GGUF -
reka-flash-3
Modelsmodel by RekaAI
RekaAI/reka-flash-3 -
Qwen3-Embedding-0.6B
Modelsfeature extraction model by Qwen · sentence-transformers
Qwen/Qwen3-Embedding-0.6B -
instructor-large
Modelssentence similarity model by hkunlp · sentence-transformers
hkunlp/instructor-large -
model by mistralai · vllm
mistralai/Devstral-Small-2-24B-Instruct-2512 -
Spark-TTS-0.5B
Modelstext to speech model by SparkAudio
SparkAudio/Spark-TTS-0.5B -
Nanbeige4.1-3B
Modelstext generation model by Nanbeige · transformers
Nanbeige/Nanbeige4.1-3B -
image text to text model by HauhauCS
HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive -
flan-t5-base
Modelsmodel by google · transformers
google/flan-t5-base -
ekko-studio
Agents & frameworksEkko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.
git clone https://github.com/EKKOLearnAI/ekko-studio.git -
Qwen3.8-27B-OBLITERATED
Modelstext generation model by OBLITERATUS · mlx
OBLITERATUS/Qwen3.8-27B-OBLITERATED -
contextgem
PromptsExtract structured data and insights from documents using LLMs and decision models
git clone https://github.com/shcherbak-ai/contextgem.git -
metavoice-1B-v0.1
Modelstext to speech model by metavoiceio · metavoice
metavoiceio/metavoice-1B-v0.1
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.