Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
atomic-agent
AI repositoriesAtomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.
git clone https://github.com/AtomicBot-ai/atomic-agent.git -
RongxinAI
Agents & frameworksOpen-source desktop AI agent: built-in free model, local GGUF models via llama.cpp, dispatch tasks from WeChat/Feishu/DingTalk. Files, browser & MCP tools. | 开源桌面 AI 智能体:内置免费模型,llama.cpp 本地 GGUF 模型,微信/飞书/钉钉直接派任务。
git clone https://github.com/rongxinzy/RongxinAI.git -
BeeLLM
Modelstext generation model by schizophyllume
schizophyllume/BeeLLM -
model by zjj1993
zjj1993/Qwen3.8-Flash-Next-uncensored-china -
phonon-40m-en
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-en -
automatic speech recognition model by nvidia · nemo
nvidia/nemotron-speech-streaming-en-0.6b -
strix-halo-guide
Datasets & benchmarksEvidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.
git clone https://github.com/hogeheer499-commits/strix-halo-guide.git -
TensorSharp
AI repositoriesA native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/iOS/Linux with full GPU capability
git clone https://github.com/zhongkaifu/TensorSharp.git -
Qwen3.8-27B-BaseQuant-V1
Modelstext generation model by basecompute
basecompute/Qwen3.8-27B-BaseQuant-V1 -
ETOS-LLM-Studio
AI repositoriesA native LLM client for iOS & Apple Watch. Run local GGUF models offline via llama.cpp, or connect to OpenAI/Claude/Gemini. Features local RAG, Model Context Protocol (MCP) tools, Siri Shortcuts, and cross-device sync. Built with Swift.
git clone https://github.com/Eric-Terminal/ETOS-LLM-Studio.git -
Box
AI repositoriesThe most advanced, fully offline client-side AI suite on Android today.
git clone https://github.com/jegly/Box.git -
model by IndrasMirror
IndrasMirror/DeepSeek-V4.1-Flash-1017-XQ-Uncensored -
text generation model by codacus
codacus/Qwen3.6-35B-A3B-MicroTurn-Duplex-LoRA -
Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2
Modelsimage text to text model by nerkyor
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 -
anon-1b
Modelstext generation model by scratchyone · transformers
scratchyone/anon-1b -
Edge0-120B-NVFP4
Modelstext generation model by Edge0 · edge0
Edge0/Edge0-120B-NVFP4 -
phonon-40m-multilingual
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-multilingual -
gguf-mcp
MCP serversInspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.
gguf-mcp@0.1.1 -
hyperflow-h3-flash
Modelsimage text to video model by VideoRebirthAI · minimax-h3
VideoRebirthAI/hyperflow-h3-flash -
unsloth
AI repositoriesLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
git clone https://github.com/unslothai/unsloth.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 -
mlx-serve
AI repositoriesNative LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
git clone https://github.com/ddalcu/mlx-serve.git -
text generation model by Maximilian228 · strata
Maximilian228/Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata -
text generation model by jimmy31chen
jimmy31chen/RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-IQ3_S-Strata
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.