Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
jev
AI repositoriesjevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.
git clone https://github.com/feder-cr/jev.git -
d1-2B-GGUF
Modelsimage text to text model by LiquidAI · gguf
LiquidAI/d1-2B-GGUF -
text generation model by FrostWolfAI · gguf
FrostWolfAI/Spark-X2.6-4B-abliterated-GGUF -
image text to text model by SC117 · gguf
SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF -
text generation model by abenzerps · gguf
abenzerps/Spark-X2.6-4B-Uncensored-GSQ-RCO-GGUF -
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 -
LumaBrowser
MCP serversLocal AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion image/video, TTS and music, plus an MCP server so Claude Code, Codex and Cline can drive your browser. Windows, macOS, Linux.
git clone https://github.com/amurgola/LumaBrowser.git -
image text to text model by JonathanColetti · transformers
JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit -
d1-Omni-2B-GGUF
Modelsaudio text to text model by LiquidAI · gguf
LiquidAI/d1-Omni-2B-GGUF -
Deskdrop
MCP serversAndroid keyboard with local AI (Ollama, Whisper, MCP) or cloud (Gemini, Groq, OpenAI)
git clone https://github.com/SvReenen/Deskdrop.git -
localmind
MCP serversA mobile application designed to provide a beautiful, fast, and privacy-respecting interface for on device LLM and local LLM servers and cloud providers
git clone https://github.com/abdulmominsakib/localmind.git -
ClawMem
AI repositoriesOn-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.
git clone https://github.com/yoloshii/ClawMem.git -
text generation model by orcarouter · gguf
orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF -
graphrag-rs
AI repositoriesGraphRAG-rs is a high-performance, state-of-the-art Rust implementation of GraphRAG (Graph-based Retrieval Augmented Generation) that builds knowledge graphs from documents and enables natural language querying with configurable entity extraction and local LLM integration
git clone https://github.com/automataIA/graphrag-rs.git -
llama-modchip
Agents & frameworksRun 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
git clone https://github.com/synchopate/llama-modchip.git -
image text to text model by Sakura721 · gguf
Sakura721/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF -
Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer
Modelsimage text to text model by nerkyor · ninfer
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer -
covert-coder
Tools & appsCovert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.
git clone https://github.com/AnonymousNomad/covert-coder.git -
apple-silicon-llm-bench
Datasets & benchmarksReproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the same model and harness, every number with its quantization and capture session; hybrid Mamba-2 models (Nemotron-3 Nano, Granite-4.0-H, Falcon-H1) included.
git clone https://github.com/john-rocky/apple-silicon-llm-bench.git -
capri-ai
Agents & frameworksCapri from Cyberpunk: Edgerunners 2 living on your desktop. A local AI desktop companion: talks, remembers you, DJs your music. 100% local, no API keys. Topics
git clone https://github.com/capri-desktop/capri-ai.git -
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 -
ai-hardware-fit
Datasets & benchmarksCan my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.
git clone https://github.com/jaeseok614/ai-hardware-fit.git -
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 -
yzma
AI repositoriesGo with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.
git clone https://github.com/hybridgroup/yzma.git
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.