Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
cli
SkillsFirecrawl CLI and agent skills: search, scrape, and interact with the web from your terminal or any coding agent, plus parse, crawl, map, Agent and Monitor. Firecrawl is the context API for AI agents.
git clone https://github.com/firecrawl/cli.git -
Mercury
Public APIsWeb parser
-
WebSearch MCP Server
MCP serversZero-API-key MCP search server: multi-engine web/academic search, PDF parsing, secure web fetch
https://github.com/daidaiJ/websearch-mcpserver/releases/download/v3.10.7-registry/websearch-mcpserver-darwin-amd64.mcpb -
Zestful
Public APIsParse recipe ingredients
-
RTFM
MCP serversLocal retrieval for AI agents: index code, docs, PDFs, data in SQLite; 24 parsers, served via MCP.
rtfm-ai@1.0.0 -
This API provides a similarity key used to match with other similar full name data when data fields are parsed into first name and last name components, including for purposes of deduplication, fuzzy matching, or merging of datasets. A much higher match rate will be achieved by matching on the similarity key rather than the data itself. This API is for full name data where first and last name…
-
TermPDF
SkillsA terminal PDF reader built for both human and agent with Rust, ratatui, PDFium, and the kitty image protocol, with smooth scrolling, link following, search, marks, presentation mode, and live watch reload
git clone https://github.com/NiJingzhe/TermPDF.git -
df0
AI repositoriesDF-0: Data processing Framework with Zero-overhead. Local-first C++20 data-processing infrastructure for deterministic, auditable, on-premise workflows. Supports 100+ formats, OCR, local AI, and opt-in cloud AI pipelines
git clone https://github.com/df0-io/df0.git -
zerikai_memory
MCP serversA standalone local-only Python MCP server that gives any IDE persistent, workspace-isolated memory. works with any IDE supporting MCP servers
git clone https://github.com/KikeVen/zerikai_memory.git -
all2md
MCP serversConvert PDF, Word, PowerPoint, HTML, email & 40+ formats to clean Markdown — and back. Built for LLMs, RAG & Python pipelines, with a built-in MCP server.
git clone https://github.com/thomas-villani/all2md.git -
dead-letter
SkillsConvert .eml and .mbox email, including Gmail Takeout, to Markdown with YAML front matter
git clone https://github.com/BigCactusLabs/dead-letter.git -
legal-skills
SkillsSkills para jurídico brasileiro — CNJ parser, revisão de contratos, contingência e classificação de audiências
git clone https://github.com/autodevx/legal-skills.git -
Url
MCP serversURL parsing & building MCP.
@pipeworx/mcp-url@0.2.1 -
Useragent
MCP serversUser-Agent parser MCP.
@pipeworx/mcp-useragent@0.2.1 -
log
MCP serversLog parse, filter, analyze for AI agents
@rog0x/mcp-log-tools@1.0.2 -
JSONSEEK
SkillsPath-based CLI for searching, inspecting, patching, and debugging JSON/JSONL files.
git clone https://github.com/lo2589/JSONSEEK.git -
story-shot-agent
Prompts剧本分镜智能体(PenShot):电影/动漫/短剧/小说→分镜片段→视频提示词。基于 LLM 通过 LangGraph+LlamaIndex实现任意格式剧本的自动解析,生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致,支持 MCP/REST API/Function Calls/A2A 集成。(LLM-powered text-to-video-prompt agent. Break scripts into Sora/Veo-ready shots with character consistency)
git clone https://github.com/neopen/story-shot-agent.git -
skills
SkillsReusable skills for document parsing and agent workflows, turning PDFs, DOCX, PPTs, and images into LLM-ready Markdown.
git clone https://github.com/PaodingAI/skills.git -
DocDigest
MCP serversCorporate email and chat thread summarization parser.
-
VoiceIntel
MCP serversAcoustic sentiment parsing and voice veracity analyzer.
-
env
MCP serversDotenv parser, ports, system info for AI agents
@rog0x/mcp-env-tools@1.0.2 -
InvoiceIn
Public APIsParse and validate received e-invoices: XRechnung, ZUGFeRD, Peppol, FatturaPA, KSeF
-
HireLayer
Public APIsParse resumes and job descriptions, normalize skills, match and rank candidates
-
DreamThreads
Public APIsParse dreams into structured entities, emotions, agency, threat, and outcomes
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.