InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. 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
  2. image text to text model by Cactus-Compute · mlx

    Indexed Hugging Face Hub, Cactus-Compute 22 ♥otherUpdated 4 days ago 1 note

    Cactus-Compute/nemotron-3.5-120b-cq
  3. Awesome-LLM-Ensemble

    Agents & frameworks

    A curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble" (IJCAI Survey 2026)

    Indexed GitHub, junchenzhi 259 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/junchenzhi/Awesome-LLM-Ensemble.git
  4. ARIS-in-AI-Offer

    AI repositories

    Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱

    Stale GitHub, wanshuiyin 640 ★MITUpdated 10 days ago

    git clone https://github.com/wanshuiyin/ARIS-in-AI-Offer.git
  5. text generation model by DavidAU

    Stale Hugging Face Hub, DavidAU 45 ♥otherUpdated 26 days ago

    DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF
  6. slotstream

    AI repositories

    Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.

    Indexed GitHub, carloslfu 673 ★MITUpdated today

    git clone https://github.com/carloslfu/slotstream.git
  7. mcp

    MCP servers

    Russian stock market data: dividends, forecasts, bond coupons, corporate calendar — MOEX

    Stale Official MCP Registry, ru.investmint Updated 4 months ago 1 note

  8. velin

    Prompts

    👩💻✍️ Prompt orchestration with Vue/React components. Compatible on any Node.js/browser runtime. No more context rendering and templating

    Indexed GitHub, moeru-ai 79 ★MITUpdated yesterday

    git clone https://github.com/moeru-ai/velin.git
  9. brazilian-dev-mcp

    MCP servers

    Utilitários para desenvolvedores brasileiros — CPF, CNPJ, CEP, telefone, moeda, dados fake e mais

    Stale Official MCP Registry, io.github.dan94k Updated 5 months ago 1 note

    brazilian-dev-mcp@1.1.0
  10. 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
  11. auv

    Skills

    📱🐭 No we are not computer use, it's Application Use Via... a unified orchestration layer of OS automation, 0 token cost

    Stale GitHub, moeru-ai 190 ★Apache-2.0Updated 21 days ago

    git clone https://github.com/moeru-ai/auv.git
  12. Pay-per-call market news, CBR/MOEX/Rosstat data and Telegram tools; auto-pays USDC on Base via x402

    Stale Official MCP Registry, io.github.Croomee Updated 25 days ago 2 notes

    x402-markettwits-mcp@0.1.0
  13. GPU Server

    MCP servers

    MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature

    Stale Official MCP Registry, io.github.moezdil Updated 26 days ago 1 note

    gpu-server@0.2.2
  14. nexflow-smf

    MCP servers

    Smart Meta-Facilitator for x402 payments on Base: route, verify, and settle payments.

    Stale Official MCP Registry, io.github.moejeaux Updated 9 months ago 2 notes

    @nexflow-smf/smf@1.0.2
  15. XGuard Live

    MCP servers

    Read current software facts with primary-source evidence and verification timestamps.

    Stale Official MCP Registry, io.github.moelayyan90 Updated 12 days ago 1 note

  16. CheckoutTruth

    MCP servers

    Verify live product price, currency, stock, variants and published shipping evidence for AI agents.

    Stale Official MCP Registry, io.github.moelayyan90 Updated 2 months ago 1 note

  17. Scoped agent execution. Server-side credentials, policy, budgets and verifiable receipts.

    Stale Official MCP Registry, io.github.moelayyan90 Updated 57 days ago 1 note

  18. Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

    Indexed OpenRouter model list, qwen Updated 9 months ago

    qwen/qwen3-coder-next
  19. NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

    Indexed OpenRouter model list, nvidia Updated 11 months ago

    nvidia/nemotron-3-nano-30b-a3b
  20. Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

    Indexed OpenRouter model list, moonshotai Updated 16 months ago

    moonshotai/kimi-k2
  21. Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

    Indexed OpenRouter model list, qwen Updated 18 months ago

    qwen/qwen3-30b-a3b
  22. NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

    Indexed OpenRouter model list, nvidia Updated 8 months ago

    nvidia/nemotron-3-super-120b-a12b
  23. 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
  24. Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

    No longer listed OpenRouter model list, stepfun Updated 9 months ago

    stepfun/step-3.5-flash

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.