InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. jev

    AI repositories

    jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.

    Stale GitHub, feder-cr 1,342 ★MITUpdated 31 days ago

    git clone https://github.com/feder-cr/jev.git
  2. d1-2B-GGUF

    Models

    image text to text model by LiquidAI · gguf

    Stale Hugging Face Hub, LiquidAI 30 ♥otherUpdated 13 days ago

    LiquidAI/d1-2B-GGUF
  3. text generation model by FrostWolfAI · gguf

    Indexed Hugging Face Hub, FrostWolfAI 39 ♥apache-2.0Updated 10 days ago

    FrostWolfAI/Spark-X2.6-4B-abliterated-GGUF
  4. image text to text model by SC117 · gguf

    Stale Hugging Face Hub, SC117 150 ♥otherUpdated 23 days ago

    SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF
  5. text generation model by abenzerps · gguf

    Stale Hugging Face Hub, abenzerps 23 ♥apache-2.0Updated 22 days ago

    abenzerps/Spark-X2.6-4B-Uncensored-GSQ-RCO-GGUF
  6. janas

    AI repositories

    37 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.

    Indexed GitHub, prabanta-dev 717 ★GPL-3.0Updated today

    git clone https://github.com/prabanta-dev/janas.git
  7. LumaBrowser

    MCP servers

    Local 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.

    Indexed GitHub, amurgola 144 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/amurgola/LumaBrowser.git
  8. image text to text model by JonathanColetti · transformers

    Stale Hugging Face Hub, JonathanColetti 25 ♥apache-2.0Updated 9 days ago

    JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit
  9. audio text to text model by LiquidAI · gguf

    Stale Hugging Face Hub, LiquidAI 22 ♥otherUpdated 13 days ago

    LiquidAI/d1-Omni-2B-GGUF
  10. Deskdrop

    MCP servers

    Android keyboard with local AI (Ollama, Whisper, MCP) or cloud (Gemini, Groq, OpenAI)

    Stale GitHub, SvReenen 62 ★GPL-3.0Updated 5 days ago

    git clone https://github.com/SvReenen/Deskdrop.git
  11. localmind

    MCP servers

    A mobile application designed to provide a beautiful, fast, and privacy-respecting interface for on device LLM and local LLM servers and cloud providers

    Stale GitHub, abdulmominsakib 306 ★MITUpdated 10 days ago

    git clone https://github.com/abdulmominsakib/localmind.git
  12. ClawMem

    AI repositories

    On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

    Stale GitHub, yoloshii 212 ★MITUpdated 9 days ago

    git clone https://github.com/yoloshii/ClawMem.git
  13. text generation model by orcarouter · gguf

    Stale Hugging Face Hub, orcarouter 20 ♥otherUpdated 16 days ago 1 note

    orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF
  14. graphrag-rs

    AI repositories

    GraphRAG-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

    Indexed GitHub, automataIA 539 ★MITUpdated today

    git clone https://github.com/automataIA/graphrag-rs.git
  15. llama-modchip

    Agents & frameworks

    Run 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).

    Indexed GitHub, synchopate 1,137 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/synchopate/llama-modchip.git
  16. image text to text model by Sakura721 · gguf

    Indexed Hugging Face Hub, Sakura721 31 ♥apache-2.0Updated 2 days ago

    Sakura721/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF
  17. image text to text model by nerkyor · ninfer

    Stale Hugging Face Hub, nerkyor 52 ♥apache-2.0Updated 29 days ago

    nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer
  18. covert-coder

    Tools & apps

    Covert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.

    Stale GitHub, AnonymousNomad 53 ★Apache-2.0Updated 34 days ago

    git clone https://github.com/AnonymousNomad/covert-coder.git
  19. apple-silicon-llm-bench

    Datasets & benchmarks

    Reproducible 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.

    Indexed GitHub, john-rocky 73 ★MITUpdated today

    git clone https://github.com/john-rocky/apple-silicon-llm-bench.git
  20. capri-ai

    Agents & frameworks

    Capri 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

    Stale GitHub, capri-desktop 155 ★Custom licence (see repository)Updated 9 days ago

    git clone https://github.com/capri-desktop/capri-ai.git
  21. ollaya

    MCP servers

    Jev-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.

    Stale GitHub, ollaya-dev 1,436 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/ollaya-dev/ollaya.git
  22. ai-hardware-fit

    Datasets & benchmarks

    Can my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.

    Indexed GitHub, jaeseok614 44 ★MITUpdated today

    git clone https://github.com/jaeseok614/ai-hardware-fit.git
  23. ContextPilot

    Prompts

    Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.

    Stale GitHub, EfficientContext 145 ★Apache-2.0Updated 25 days ago

    git clone https://github.com/EfficientContext/ContextPilot.git
  24. yzma

    AI repositories

    Go with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.

    Stale GitHub, hybridgroup 652 ★Custom licence (see repository)Updated 32 days ago

    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.