InnerVault

Library

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

Results

  1. xVerify

    Datasets & benchmarks

    xVerify: Efficient Answer Verifier for Reasoning Model Evaluations

    Stale GitHub, IAAR-Shanghai 150 ★Custom licence (see repository)Updated 19 days ago

    git clone https://github.com/IAAR-Shanghai/xVerify.git
  2. benspdf

    MCP servers

    Read PDFs locally: text, pages, metadata, scan detection, layout, permissions, render, OCR.

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

    benspdf-mcp@0.3.0
  3. Inbox Benefits MCP

    MCP servers

    Read-only multi-inbox benefits radar with local deduplication and explicit account health.

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

    https://github.com/fvegiard/agent-infra/releases/download/inbox-benefits-v0.1.0/inbox-benefits-mcp.mcpb
  4. Checks receipt of the Continuous Cash Benefit (BPC) by a beneficiary from the CPF and NIS. Platform-

    Stale Official MCP Registry, io.github.mcp-dir Updated 3 months ago 1 note

  5. Bench Agent Discovery

    MCP servers

    Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.

    Stale Official MCP Registry, io.github.VirajMishra1 Updated 4 months ago 1 note

  6. mcp-benchmark-hygiene

    MCP servers

    Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.

    Stale Official MCP Registry, io.github.sudo-ai-git Updated 2 months ago 1 note

    mcp-benchmark-hygiene@1.0.1
  7. AI Benchmark Index

    MCP servers

    Search 264 AI benchmarks by category, with data sources and licences for each.

    Stale Official MCP Registry, com.aibenchmarkindex Updated 31 days ago 1 note

  8. Eclipse Benchkit

    MCP servers

    Free vendor self-bench SDK — Assay scorecard format + verifier spot-check sampling.

    Stale Official MCP Registry, io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC Updated 20 days ago

  9. mac-ml-speed-test

    Datasets & benchmarks

    A few quick scripts focused on testing TensorFlow/PyTorch/Llama 2 on macOS.

    Stale GitHub, mrdbourke 203 ★Updated 2 years ago

    git clone https://github.com/mrdbourke/mac-ml-speed-test.git
  10. sloptotal

    Datasets & benchmarks

    Open-source AI text detector and ChatGPT detector: 23 engines, one calibrated score, every number measured on a public benchmark. Self-hosted, runs on CPU.

    Stale GitHub, pablocaeg 98 ★MITUpdated 13 days ago

    git clone https://github.com/pablocaeg/sloptotal.git
  11. Bench47

    MCP servers

    Shared Markdown memory for your agents: docs, typed collections, files, skills and Dispatch.

    Stale Official MCP Registry, com.bench47 Updated 11 days ago 1 note

  12. Bahrain payments for AI agents — Benefit via Tap Payments. Never holds funds.

    Stale Official MCP Registry, app.wishpool Updated 4 months ago 1 note

  13. Who qualifies for 10,956 Korean government benefits (보조금24). Plus public data and weather.

    Stale Official MCP Registry, site.star365 Updated 2 months ago 1 note

  14. Benchwarmers

    MCP servers

    Ask a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.

    Stale Official MCP Registry, io.github.WendellResearch-AI Updated 3 days ago 2 notes

    @wendellresearch-ai/benchwarmers@0.6.9
  15. TwinFix

    Datasets & benchmarks

    TwinFix — AI agent that diagnoses, reproduces and fixes bugs in a disposable twin environment. 在一次性孪生环境中自动诊断、复现并修复故障的 AI Agent。

    Indexed GitHub, spacesky-cell 117 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/spacesky-cell/TwinFix.git
  16. Mercedes-Benz

    Public APIs

    Telematics data, remotely access vehicle functions, car configurator, locate service dealers

    Indexed public-apis (GitHub list)

  17. SkillCorpus

    Skills

    Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

    Stale GitHub, EverMind-AI 700 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/EverMind-AI/SkillCorpus.git
  18. tne-sdk

    Skills

    TNE-SDK - The Official Python SDK for The Null Epoch - an AI-only MMO where LLMs play autonomously. Connect any model (OpenAI, Anthropic, Ollama, vLLM, etc.) via MCP, TUI launcher, or raw HTTP. Includes memory, reflection, and agent orchestration for persistent AI gameplay/benchmarking.

    Stale GitHub, Firespawn-Studios 14 ★MITUpdated 17 days ago

    git clone https://github.com/Firespawn-Studios/tne-sdk.git
  19. LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.

    Stale Official MCP Registry, ai.theaggregate Updated 38 days ago 1 note

  20. Imagine AI Benchmark

    MCP servers

    LinkedIn content benchmark for 900+ B2B companies and their teams, with an open scoring method.

    Stale Official MCP Registry, ai.useimagine Updated 37 days ago 1 note

  21. French family-benefit models (CNAF corpus) as executable rules with sources; independent demo

    Stale Official MCP Registry, io.arxo Updated 33 days ago 2 notes

    @arxo/mcp-cnaf@0.1.1
  22. Armenia state register lookup with beneficial owners from official BODS declarations.

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

  23. Manage Benchmark Email lists and contacts, and read campaign reports: opens, clicks, bounces.

    Indexed Official MCP Registry, io.usefulapi Updated today 1 note

  24. Benefits Intake

    Public APIs

    The Benefits Intake API allows authorized third-party systems used by Veteran Service Organizations (VSOs), agencies, and Veterans to digitally submit VA benefits claim documents directly to the Veterans Benefits Administration's (VBA) claims intake process. This API handles documents related to the following benefit claim types: Compensation Pension/Survivors Benefits Education Fiduciary…

    Indexed APIs.guru OpenAPI Directory, va.gov Updated 3 years ago

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.