InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. voxlock

    Models

    audio to audio model by arbazsiddiqui

    Stale Hugging Face Hub, arbazsiddiqui 24 ♥apache-2.0Updated 35 days ago

    arbazsiddiqui/voxlock
  2. oneDNN

    AI repositories

    Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.

    Indexed GitHub, uxlfoundation 4,094 ★Apache-2.0Updated today

    git clone https://github.com/uxlfoundation/oneDNN.git
  3. vera

    AI repositories

    Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

    Indexed GitHub, VeraTools 148 ★MITUpdated 4 days ago

    git clone https://github.com/VeraTools/vera.git
  4. 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
  5. memex

    MCP servers

    Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.

    Stale Official MCP Registry, io.github.ayushagrawal288 Updated 5 months ago 1 note

    ghcr.io/ayushagrawal288/memex:v0.1.0
  6. model-scanner

    MCP servers

    Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks

    Stale Official MCP Registry, io.github.4hmetuyar Updated 49 days ago 1 note

    @guardbee/mcp-model-scanner@0.1.2
  7. OmniMem

    MCP servers

    Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills compiled from what worked, plus knowledge from the RSS feeds you read. One Rust binary on SQLite: a tray app for macOS, Windows and Linux, or a server.

    Indexed GitHub, richarvey 95 ★MITUpdated 4 days ago

    git clone https://github.com/richarvey/OmniMem.git
  8. velocirag

    MCP servers

    Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.

    Stale Official MCP Registry, io.github.HaseebKhalid1507 Updated 7 months ago 1 note

    velocirag@0.7.4
  9. ContextBridge

    MCP servers

    MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.

    Stale Official MCP Registry, io.github.ThunderEagle Updated 4 months ago 1 note

    ThunderEagle.ContextBridge@1.0.2
  10. hayward

    MCP servers

    Checks ML model files (pickle, PyTorch, joblib, NumPy, GGUF, ONNX) for code that runs on load.

    Stale Official MCP Registry, io.github.hedgerow-dev Updated 24 days ago 1 note

    hayward@1.4.1
  11. GenClass

    Skills

    GenClass Runtime: a 10 MB in-browser model that detects race conditions, stale responses and duplicate requests in web apps; opt-in guard mode can prevent some of them. npm i @genclass/runtime

    Indexed GitHub, genclass-dev 11 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/genclass-dev/GenClass.git
  12. knowledge-rag

    AI repositories

    Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.

    Indexed GitHub, lyonzin 306 ★MITUpdated yesterday

    git clone https://github.com/lyonzin/knowledge-rag.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.