InnerVault

Library

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

Results

  1. sublinear-time-solver

    MCP servers

    Rust + WASM sublinear-time solver for asymmetric diagonally dominant systems. Exposes Neumann series, push, and hybrid random-walk algorithms with npm/npx CLI and Flow-Nexus HTTP streaming for swarm cost propagation and verification.

    Stale GitHub, ruvnet 93 ★MITUpdated 6 days ago

    git clone https://github.com/ruvnet/sublinear-time-solver.git
  2. Act as a Prompt Refinement AI. Inputs: - Original prompt: ${originalPrompt} - Feedback (optional): ${feedback} - Iteration count: ${iterationCount} - Mode (default = "strict"): strict | creative | hybrid - Use case…

    Indexed prompts.chat (CC0 prompt collection), kj5irq@gmail.com CC0-1.0

  3. aos

    Skills

    A Curated AI AGENT OS – Optimized agent skills and add-ons like memB, OpenWiki, Heimdall Token Saver, and Godmode architectures.

    Stale GitHub, hybridlabor-api 7 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/hybridlabor-api/aos.git
  4. specwise-mcp

    MCP servers

    OpenAPI and JSON Schema validation and OpenAPI breaking-change diffs for AI agents.

    Stale Official MCP Registry, io.github.hybridforgelab Updated 11 days ago 3 notes

    hybridforgelab-specwise-mcp@0.2.3
  5. Deuz-SDK

    Agents & frameworks

    TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge.

    Stale GitHub, Deuz-AI 563 ★MITUpdated 32 days ago

    git clone https://github.com/Deuz-AI/Deuz-SDK.git
  6. 75 paid agent tools: website audits and research; BM25, MiniLM vector and hybrid discovery are free.

    Stale Official MCP Registry, io.github.Its-fortunatefolly Updated 12 days ago 1 note

  7. distill-mcp

    MCP servers

    Web pages to clean Markdown for AI agents, honouring robots.txt and AI opt-outs.

    Stale Official MCP Registry, io.github.hybridforgelab Updated 11 days ago 3 notes

    hybridforgelab-distill-mcp@0.2.3
  8. TeamAgentMemory

    MCP servers

    Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and department/team/member isolation. SQLite or Postgres, any OpenAI-compatible LLM.

    Indexed GitHub, hsuanshao 39 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/hsuanshao/TeamAgentMemory.git
  9. NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    Indexed OpenRouter model list, nvidia Updated 5 months ago

    nvidia/nemotron-3-ultra-550b-a55b
  10. shipshape-mcp

    MCP servers

    Dockerfile and Kubernetes lint for AI agents: Pod Security Standards, A–F grade, a fix per finding.

    Stale Official MCP Registry, io.github.hybridforgelab Updated 11 days ago 3 notes

    hybridforgelab-shipshape-mcp@0.2.3
  11. Cortex

    Skills

    Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

    Indexed GitHub, cdeust 77 ★MITUpdated yesterday

    git clone https://github.com/cdeust/Cortex.git
  12. NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    Indexed OpenRouter model list, nvidia Updated 5 months ago

    nvidia/nemotron-3-ultra-550b-a55b:free
  13. Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

    Indexed OpenRouter model list, nousresearch Updated 14 months ago

    nousresearch/hermes-4-405b
  14. MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...

    No longer listed OpenRouter model list, minimax Updated 17 months ago

    minimax/minimax-m1
  15. DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

    Indexed OpenRouter model list, deepseek Updated 15 months ago

    deepseek/deepseek-chat-v3.1
  16. unfold-mcp

    MCP servers

    PDF, DOCX, PPTX and XLSX documents to Markdown for AI agents, from a URL or a local file.

    Stale Official MCP Registry, io.github.hybridforgelab Updated 11 days ago 3 notes

    hybridforgelab-unfold-mcp@0.2.3
  17. Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

    Indexed OpenRouter model list, qwen Updated 6 months ago

    qwen/qwen3.6-27b
  18. Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.

    Indexed OpenRouter model list, kt Updated 12 days ago

    kt/midm-k-3.0-pro
  19. Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...

    Indexed OpenRouter model list, inclusionai Updated 4 days ago

    inclusionai/ling-3.2-flash:free
  20. The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-flash-02-23
  21. Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

    Indexed OpenRouter model list, qwen Updated 7 months ago

    qwen/qwen3.6-plus
  22. memo

    MCP servers

    Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.

    Stale GitHub, jagoff 26 ★MITUpdated 13 days ago

    git clone https://github.com/jagoff/memo.git
  23. m3-memory

    MCP servers

    Local-first memory backend for AI agents · 99.2% LongMemEval-S retrieval @ k=8 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable

    Stale GitHub, skynetcmd 30 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/skynetcmd/m3-memory.git
  24. The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-35b-a3b

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.