InnerVault

Library

87,734 resources from 11 public sources. 46 checked by hand. The rest are indexed automatically and not reviewed.

Results

7,031 results with any of your words Clear search and filters
  1. Arena rates 399 text models from 52 labs, up from 10 models in May 2023. Yet only 5 labs hold.

    Stale com.modevc · via Official MCP Registry Updated 32 days ago 1 note

  2. cfgaudit

    MCP servers

    Static security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. SARIF output, OWASP LLM Top 10 mapping.

    Indexed cfgaudit · via GitHub 27 ★Apache-2.0Updated yesterday

    Source for cfgaudit (opens github.com) git clone https://github.com/cfgaudit/cfgaudit.git
  3. deepmark

    Datasets & benchmarks

    Deepmark AI enables a unique testing environment for language models (LLM) assessment on task-specific metrics and on your own data so your GenAI-powered solution has predictable and reliable performance.

    Stale IngestAI · via GitHub 104 ★AGPL-3.0Updated 2 years ago

    Source for deepmark (opens github.com) git clone https://github.com/IngestAI/deepmark.git
  4. deltallm

    MCP servers

    Self-hosted LLM gateway with SSO, audit logs, client access controls, routing, and usage tracking. OpenAI-compatible and MIT licensed.

    Indexed deltawi · via GitHub 21 ★MITUpdated yesterday

    Source for deltallm (opens github.com) git clone https://github.com/deltawi/deltallm.git
  5. 8 个游戏美术 Agent Skills:像素精灵、Spine 骨骼动画、方块角色(Blockbench)与讲解配音。附可复用代码、资源来源、验证记录和效果示例。

    Stale zeroa234 · via GitHub 11 ★Updated 32 days ago

    Source for game-asset-aesthetic-test (opens github.com) git clone https://github.com/zeroa234/game-asset-aesthetic-test.git
  6. DishwasherBench

    Datasets & benchmarks

    A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The game inside is called Spotless.

    Stale composo-ai · via GitHub 71 ★MITUpdated 33 days ago

    Source for DishwasherBench (opens github.com) git clone https://github.com/composo-ai/DishwasherBench.git
  7. Basic arithmetic tools with natural-language expression parsing and evaluation.

    Stale io.github.yarnabrina · via Official MCP Registry Updated 33 days ago 1 note

  8. humanjs

    MCP servers

    Humanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it over MCP from your favorite AI.

    Stale totigm · via GitHub 23 ★MITUpdated 18 days ago

    Source for humanjs (opens github.com) git clone https://github.com/totigm/humanjs.git
  9. seekstone

    MCP servers

    The Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window. Filesystem-direct: single-digit-ms keyword search, ~26 ms local semantic search, ~2 KB payloads, 25 tools.

    Indexed shaqmughal · via GitHub 35 ★MITUpdated 4 days ago

    Source for seekstone (opens github.com) git clone https://github.com/shaqmughal/seekstone.git
  10. model-card-lint-gpai

    MCP servers

    Lints a Hugging Face model card against the Hub metadata spec and the EU AI Act general-purpose AI d

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

    Source for model-card-lint-gpai (opens github.com) @readystack/model-card-lint-gpai@1.0.3
  11. Find open biology and chemistry AI models, bioinformatics tools and databases, and run them online.

    Stale com.corollary-labs · via Official MCP Registry Updated 30 days ago 1 note

  12. Find GitHub tools and Hugging Face models: source links, licenses, setup notes and review dates.

    Stale io.github.myworkingmemory · via Official MCP Registry Updated 22 days ago 1 note

  13. The best open model trails the best closed model by 42 Arena points. In a blind vote it would.

    Stale com.modevc · via Official MCP Registry Updated 32 days ago 1 note

  14. run402

    MCP servers

    Full-stack backend infrastructure for AI agents: Postgres, auth, storage, serverless functions and atomic deploys. TypeScript SDK, CLI and MCP server. Paid with x402/MPP. Open source.

    Indexed kychee-com · via GitHub 24 ★MITUpdated yesterday

    Source for run402 (opens github.com) git clone https://github.com/kychee-com/run402.git
  15. ai model card

    Prompts

    Ask me for AI model name(s) in next message * You are an AI model research expert. You must research and provide actual and accurate data, never make up any data. * research and list the specification of the AI model…

    Indexed sxlderek@gmail.com · via prompts.chat (CC0 prompt collection) CC0-1.0

  16. pain001

    MCP servers

    Generate and validate ISO 20022 payment files (pain.001 v03-v12, pain.008) from CSV, SQLite, JSON, or Parquet. XSD and SEPA scheme validation, pain.002 and camt.053 parsers and builders, plus a CLI, REST API, MCP server, and LSP server for editor diagnostics. 🐍

    Stale sebastienrousseau · via GitHub 49 ★Apache-2.0Updated 9 days ago

    Source for pain001 (opens github.com) git clone https://github.com/sebastienrousseau/pain001.git
  17. Zero-auth email OTP extractor, KV checkpoints, webhook bins, wake timers, and markdown reader.

    Stale tools.model · via Official MCP Registry Updated 21 days ago 1 note

  18. modelranch

    MCP servers

    A free deals network for AI agents: post what your person has and needs, find agents who can help.

    Indexed com.modelranch · via Official MCP Registry Updated 2 days ago 1 note

  19. CoalTipple

    Skills

    Safe, quality-gated model+effort router for Claude Code - delegates cheap work down to save tokens, escalates hard/sensitive work up through a verify staircase, never-down gate, and fail-safe Lock, up to a consent-gated fable top rung. Not the cheapest router; the safest one inside Claude.

    Stale TheColliery · via GitHub 8 ★Apache-2.0Updated 4 days ago

    Source for CoalTipple (opens github.com) git clone https://github.com/TheColliery/CoalTipple.git
  20. Automatically filters and aggregates AI news, extracts article data, and produces actionable commercial intelligence.

    Stale alphaparkinc · via GitHub 9 ★MITUpdated 19 days ago

    Source for openclaw-genpark-signal-aggregator (opens github.com) git clone https://github.com/alphaparkinc/openclaw-genpark-signal-aggregator.git
  21. multi-agents

    Datasets & benchmarks

    Multi-agent teams for real work: run teams of coding agents (Claude Code, Codex, any model) in isolated git worktrees, and measure whether the team beats a solo agent on cost and results.

    Stale BichengWang · via GitHub 158 ★MITUpdated 11 days ago

    Source for multi-agents (opens github.com) git clone https://github.com/BichengWang/multi-agents.git
  22. Neuronto Agentic Resource Discovery (ARD) Index. Federated search across every public ARD registry, plus a verified tool index read from each MCP server's own tools/list, hybrid lexical and semantic retrieval, and ARD-Bench.

    Stale neuronto · via GitHub 55 ★Apache-2.0Updated 16 days ago

    Source for agentic-resource-discovery (opens github.com) git clone https://github.com/neuronto/agentic-resource-discovery.git
  23. bagidea-office

    Agents & frameworks

    A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappable models (Claude/GLM/DeepSeek/Qwen/Kimi/OpenAI/Gemini/Groq/Ollama…), workflows, plugins, voice & Telegram/Discord/LINE. Open source.

    Stale bagidea · via GitHub 260 ★MITUpdated 19 days ago

    Source for bagidea-office (opens github.com) git clone https://github.com/bagidea/bagidea-office.git
  24. Act as a Vacuum Arc Modeling Expert. You are a professor-level specialist in vacuum arc theory and Fluent-based modeling, with expertise in writing UDFs and UDSs. Your task is to model vacuum arcs under transverse…

    Indexed 1047988931@qq.com · via prompts.chat (CC0 prompt collection) CC0-1.0

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.