InnerVault

Library

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

Results

537 results with any of your words Clear search and filters
  1. Humanuscrit — HAPP

    MCP servers

    Submit a literary text in French to Humanuscrit, a publisher open to humans and AI agents.

    Stale Official MCP Registry, com.humanuscrit Updated 50 days ago 1 note

  2. GrayMatter

    MCP servers

    Secure durable memory and bounded context for AI agents, with hosted OAuth and local Lite support.

    Stale Official MCP Registry, io.github.ValkyrLabs Updated 42 days ago 1 note

  3. nano-banana-mcp

    MCP servers

    AI image generation and editing with Google Gemini: Nano Banana 2.1, Pro and Lite models

    Stale Official MCP Registry, io.github.fjacquet Updated 9 days ago 2 notes

    @fjacquet/nano-banana-mcp@3.3.0
  4. For platform engineers on AKS: 28 rules naming every removed apiVersion, literal credential and :lat

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

    @readystack/cloud-manifest-audit-kit@0.1.1
  5. Estimate hours and cost of systematic or literature reviews: screening and full-text reading.

    Stale Official MCP Registry, com.realmarketlabs.tools Updated 13 days ago 1 note

  6. Zovo Paper Finder

    MCP servers

    Build a literature list for a student paper, thesis or research project from Crossref.

    Stale Official MCP Registry, io.github.theluckystrike Updated 9 days ago 1 note

  7. forest

    Agents & frameworks

    FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence

    Stale GitHub, mikamikasuki 355 ★Apache-2.0Updated 21 days ago

    git clone https://github.com/mikamikasuki/forest.git
  8. SEDRA IV API

    Public APIs

    The SEDRA API is documented in OpenAPI format and uses ReDoc (https://github.com/Rebilly/ReDoc) for documentation. Introduction This document describes the JSON API for the Syriac Electronic Data Research Archive (SEDRA). The SEDRA project is a linguistic and literary database of Syriac language and literature focusing on providing electronic access to the corpus of Syriac lexicons with…

    Indexed APIs.guru OpenAPI Directory, bethmardutho.org Updated 5 years ago

  9. Source Library

    MCP servers

    Search 15K rare pre-modern texts translated to English: philosophy, religion, science, literature.

    Stale Official MCP Registry, io.github.Embassy-of-the-Free-Mind Updated 12 days ago 1 note

  10. Germline ACMG/AMP classification, genes, disease associations, literature and API-key case analysis.

    Stale Official MCP Registry, io.github.helena-bioinformatics Updated 12 days ago 1 note

  11. TON liteservers over ADNL: balances, history, get-methods, non-custodial DEX and cross-chain swaps

    Stale Official MCP Registry, io.github.tonnode Updated 42 days ago 2 notes

    @tonnode/mcp@0.9.2
  12. uxlint

    MCP servers

    Audit a site's UX the way a design-literate reviewer would, with a concrete fix for every finding.

    Stale Official MCP Registry, io.github.uxlint-net Updated 3 months ago 1 note

    @uxlint-net/uxlint@0.1.30
  13. Read-only psilocybin literature, trial facts, citations and verified bibliographic datasets.

    Stale Official MCP Registry, com.psilocybin-research Updated 11 days ago 1 note

  14. Fuse

    MCP servers

    Faster .NET build and test loop for AI coding agents.

    Stale GitHub, Litenova-Solutions 36 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/Litenova-Solutions/Fuse.git
  15. Read-only pool salt dosing, bag counts, optional costs, and water volume in US gallons and liters.

    Stale Official MCP Registry, com.poolcarecalculators Updated 34 days ago 1 note

  16. turbo-flow

    Agents & frameworks

    The rules layer for AI-written code — rig-lite: a fail-closed cross-model review gate, a written constitution, git-versioned memory. Any harness, any repo. v1-4 were the agentic dev environment.

    Indexed GitHub, marcuspat 185 ★MITUpdated 5 days ago

    git clone https://github.com/marcuspat/turbo-flow.git
  17. 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
  18. 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
  19. 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
  20. 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
  21. 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
  22. 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
  23. 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
  24. crux

    Skills

    A scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki, a task manager, and a local browser GUI cockpit.

    Stale GitHub, mehdiforoozandeh 18 ★MITUpdated 17 days ago

    git clone https://github.com/mehdiforoozandeh/crux.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.