InnerVault

Library

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

Results

  1. Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

    Indexed OpenRouter model list, cohere Updated 20 months ago

    cohere/command-a
  2. alzeo

    Agents & frameworks

    Alzeo is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Acer), into a private AI server in one command: measured model lanes, OpenAI and Anthropic APIs, and a local cockpit.

    Stale GitHub, hasso5703 258 ★MITUpdated 5 days ago

    git clone https://github.com/hasso5703/alzeo.git
  3. the-agency

    Skills

    Claude Code, fixed for everyone. Memory that survives sessions, agents that finish what they start, QA gates before 'done', the right model for each job. 235+ skills. Installs to ~/.claude/ — no cloud, no extra keys.

    Indexed GitHub, Tekkiiiii 7 ★MITUpdated 3 days ago

    git clone https://github.com/Tekkiiiii/the-agency.git
  4. Free open-source Claude Code kit: 22 AI agents (17 + 5 UEFN MCP sub-agents), 34 skills and 387 proven UEFN MCP recipes to build, test and improve Fortnite maps (Verse, Niagara, UI)

    Indexed GitHub, mimmo-the-root 18 ★MITUpdated yesterday

    git clone https://github.com/mimmo-the-root/UEFN-dream-bot-team.git
  5. Lynn

    Agents & frameworks

    开源桌面 AI Agent 与 CLI:长期记忆、多 Agent、实时语音;Qwen3.8-27B Coder390 EfficientThink 本地 GGUF(llama.cpp Q2/Q3,内置 Q4 MTP)· Open-source desktop AI agent & CLI with Coder390 local models

    Indexed GitHub, MerkyorLynn 71 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/MerkyorLynn/Lynn.git
  6. 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
  7. Let AI read and edit the open model in Revit, AutoCAD, Civil 3D, Navisworks and 5 more Autodesk apps

    Stale Official MCP Registry, com.aecpilot Updated 4 days ago

  8. md-to-word

    Skills

    Deterministic Markdown-to-Word (.docx) compiler & MCP server for academic papers, theses and AI agents | 确定性 Markdown 转规范 Word 与 MCP 服务

    Indexed GitHub, ls-open 17 ★MITUpdated 3 days ago

    git clone https://github.com/ls-open/md-to-word.git
  9. 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
  10. the-pair

    Agents & frameworks

    Open-source AI pair programming desktop app: a read-only Mentor and an Executor agent cross-check each other's code to catch AI mistakes before they land. Bring any model — Claude, GPT, Gemini, Kimi, GLM, Qwen or local Ollama. No agent CLI needed. macOS / Windows / Linux.

    Indexed GitHub, timwuhaotian 390 ★Apache-2.0Updated yesterday

    git clone https://github.com/timwuhaotian/the-pair.git
  11. 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
  12. 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
  13. Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...

    Indexed OpenRouter model list, recursive Updated 26 days ago

    recursive/flint-v1.0:free
  14. NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

    Indexed OpenRouter model list, nvidia Updated 3 months ago

    nvidia/nemotron-3.5-lightning
  15. Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

    Indexed OpenRouter model list, meta Updated 3 months ago

    meta/muse-glimmer-30b
  16. 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
  17. Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

    Indexed OpenRouter model list, moonshotai Updated 12 months ago

    moonshotai/kimi-k2-thinking
  18. 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
  19. mcp-server

    MCP servers

    Open-source MCP server for AI agents (MIT): read across 43 ad platforms ($0.00/mo, 0% ad spend markup), with verified campaign write and create across 16 core platforms ($20.00/mo SOLO, $500.00/mo SCALE), multi-tenant OAuth, server-enforced spend guardrails, and REST/SDKs.

    Stale GitHub, Synter-Media-AI 21 ★MITUpdated 4 days ago

    git clone https://github.com/Synter-Media-AI/mcp-server.git
  20. NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

    Indexed OpenRouter model list, nvidia Updated 3 months ago

    nvidia/nemotron-3.5-lightning:free
  21. Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

    Indexed OpenRouter model list, meta Updated 3 months ago

    meta/muse-glimmer-30b:batch
  22. Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

    Indexed OpenRouter model list, moonshotai Updated 4 months ago

    moonshotai/kimi-k3
  23. gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

    Indexed OpenRouter model list, openai Updated 15 months ago

    openai/gpt-oss-20b
  24. LeafLoom

    Skills

    Local-first knowledge base & personal wiki for Markdown and HTML. Keep files and search on your computer. Connect ChatGPT, MCP, Skills and AI Chat, with source-linked search and a knowledge graph. Open source. 本地知识库 · 个人 Wiki · 知识管理

    Stale GitHub, DJ-Huang 6 ★MITUpdated 7 days ago

    git clone https://github.com/DJ-Huang/LeafLoom.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.