Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
tweet_eval
Datasets & benchmarksHugging Face dataset by cardiffnlp
cardiffnlp/tweet_eval -
trivia_qa
Datasets & benchmarksHugging Face dataset by mandarjoshi
mandarjoshi/trivia_qa -
Company formation, registered agents, EINs and annual filings, set out as one brief to quote.
-
GPT-5.5-Gemini-3.1-Pro-Grok-4-Claude-Fable-5-Mythos-5-Qwen-3.7-Max-and-more-Distillation-Dataset
Datasets & benchmarksHugging Face dataset by Manusagents
Manusagents/GPT-5.5-Gemini-3.1-Pro-Grok-4-Claude-Fable-5-Mythos-5-Qwen-3.7-Max-and-more-Distillation-Dataset -
Zero-To-CAD-1m
Datasets & benchmarksHugging Face dataset by ADSKAILab
ADSKAILab/Zero-To-CAD-1m -
remnic
MCP serversOpen-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
git clone https://github.com/joshuaswarren/remnic.git -
CodeX-2M-Thinking
Datasets & benchmarksHugging Face dataset by Modotte
Modotte/CodeX-2M-Thinking -
sharegpt_gpt4
Datasets & benchmarksHugging Face dataset by shibing624
shibing624/sharegpt_gpt4 -
Lovie Company Formation
MCP serversForm companies, manage bank accounts, cards, invoices and more — directly from your AI coding tools.
lovie@1.0.10 -
codefmt
MCP serversFormat/lint JS, Python, HubL for automation platforms. Tools: format_code, format_json, ask_codefmt
-
awesome-reverse-engineering
SkillsCurated reverse-engineering tools and learning resources for binaries, apps, firmware, formats, and protocols.
git clone https://github.com/morluto/awesome-reverse-engineering.git -
ebook-mcp
MCP serversA MCP server that supports mainstream eBook formats including EPUB, PDF and more. Simplify your eBook user experience with LLM.
git clone https://github.com/onebirdrocks/ebook-mcp.git -
multilingual_librispeech
Datasets & benchmarksHugging Face dataset by facebook
facebook/multilingual_librispeech -
Vaani
Datasets & benchmarksHugging Face dataset by ARTPARK-IISc
ARTPARK-IISc/Vaani -
prompty
AI repositoriesPrompty makes it easy to create, manage, debug, and evaluate LLM prompts for your AI applications. Prompty is an asset class and format for LLM prompts designed to enhance observability, understandability, and portability for developers.
git clone https://github.com/microsoft/prompty.git -
zenith
MCP serversA design document format built for the age of AI agents. Zenith is a plain-text format and engine for design files — posters, decks, books, social graphics, and more
git clone https://github.com/zenitheditor/zenith.git -
coyo-700m
Datasets & benchmarksHugging Face dataset by kakaobrain
kakaobrain/coyo-700m -
x402 Format Checker
MCP serversIBAN, EU VAT, NIP, REGON, PESEL, email checks. Only $0.001 (0.1 cent) per check via x402 on Base
-
AI Content Repurposer Tool: URL to 9 Formats
MCP serversTurn any URL or text into Twitter threads, LinkedIn posts, Instagram captions, YouTube titles and…
-
okf-agent-memory
MCP serversGit-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
git clone https://github.com/okf-memory/okf-agent-memory.git -
claude-design-card
SkillsClaude Code skill for generating design cards in 14 formats — platform covers, social sharing cards, and editorial layouts following Anthropic
git clone https://github.com/geekjourneyx/claude-design-card.git -
super_glue
Datasets & benchmarksHugging Face dataset by aps
aps/super_glue -
rea-video
SkillsReverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 逆向一切视频,逐个镜头看是拍的、AI 生成的还是代码做的,再告诉你怎么复刻;拆解结果按 VIDEO.md 格式输出。
git clone https://github.com/JuneYaooo/rea-video.git -
Sema
MCP serversMCP tools for Sema — eval, compile, build, format, and docs for a Lisp with LLM primitives.
https://github.com/sema-lisp/sema/releases/download/v2.0.0/sema.mcpb@2.0.0
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.