Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Phi-4-reasoning-plus
Modelstext generation model by microsoft · transformers
microsoft/Phi-4-reasoning-plus -
replit-code-v1_5-3b
Modelstext generation model by replit · transformers
replit/replit-code-v1_5-3b -
Meta-Llama-Guard-2-8B
Modelstext generation model by meta-llama · transformers
meta-llama/Meta-Llama-Guard-2-8B -
Qwen2-VL-72B-Instruct
Modelsimage text to text model by Qwen · transformers
Qwen/Qwen2-VL-72B-Instruct -
MinerU2.5-2509-1.2B
Modelsimage text to text model by opendatalab · transformers
opendatalab/MinerU2.5-2509-1.2B -
Llama3-ChatQA-1.5-70B
Modelstext generation model by nvidia · transformers
nvidia/Llama3-ChatQA-1.5-70B -
ContextPilot
PromptsAccelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.
git clone https://github.com/EfficientContext/ContextPilot.git -
wllama
AI repositoriesWebAssembly binding for llama.cpp - Enabling on-browser LLM inference
git clone https://github.com/ngxson/wllama.git -
laya
AI repositoriesRun Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime
git clone https://github.com/receptron/laya.git -
Qwen3.8-27B-DFlash2
Modelstext generation model by z-lab · transformers
z-lab/Qwen3.8-27B-DFlash2 -
Nanonets-OCR2-3B
Modelsimage text to text model by nanonets · transformers
nanonets/Nanonets-OCR2-3B -
larql
AI repositoriesRun, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.
git clone https://github.com/chrishayuk/larql.git -
AI-Engineer-Headquarters
AI repositoriesA collection of scientific methods, processes, algorithms, and systems to build stories & models.
git clone https://github.com/hemansnation/AI-Engineer-Headquarters.git -
Hermes-2-Pro-Mistral-7B
Modelstext generation model by NousResearch · transformers
NousResearch/Hermes-2-Pro-Mistral-7B -
ms-marco-MiniLM-L6-v2
Modelstext ranking model by cross-encoder · sentence-transformers
cross-encoder/ms-marco-MiniLM-L6-v2 -
incognide
Agents & frameworksExplore the unknown, build the future, own your data.
git clone https://github.com/NPC-Worldwide/incognide.git -
nomic-embed-text-v1
Modelssentence similarity model by nomic-ai · sentence-transformers
nomic-ai/nomic-embed-text-v1 -
MNN-Pocket-0.3B
Modelstext generation model by taobao-mnn · transformers
taobao-mnn/MNN-Pocket-0.3B -
ollaya
MCP serversJev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench.
git clone https://github.com/ollaya-dev/ollaya.git -
Llama-3.1-405B-Instruct
Modelstext generation model by meta-llama · transformers
meta-llama/Llama-3.1-405B-Instruct -
lemonade
MCP serversLemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
git clone https://github.com/lemonade-sdk/lemonade.git -
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 -
llava-v1.6-mistral-7b-hf
Modelsimage text to text model by llava-hf · transformers
llava-hf/llava-v1.6-mistral-7b-hf -
all-MiniLM-L12-v2
Modelssentence similarity model by sentence-transformers · sentence-transformers
sentence-transformers/all-MiniLM-L12-v2
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.