The package manager for AI agents
Package the building blocks of agent systems once, version them cleanly, and make them portable across runtimes, frameworks, and ecosystems.
brew tap agentpm-dev/tap
brew install agentpmscoop bucket add agentpm https://github.com/agentpm-dev/scoop-bucket
scoop install agentpmagentpm install @ns/toolnameconst t = await load('@ns/toolname');t = load("@ns/tooname");Trending tools
Summarize long text to a concise abstract.
Translate text into a target language using LLM.
Convert raw HTML into Markdown and plain text, with optional main-content extraction.
Make HTTP requests (GET/POST/etc.) and return normalized response metadata and content.
Fetch a Wikipedia URL and return title, text, and image URLs.
Extract text from PDFs, either from a URL or base64-encoded PDF data.
Fetch a web page and return cleaned content, metadata, and discovered links.
Read and update GitHub issues using a compact, agent-friendly action surface.
Crawl a bounded set of pages while respecting robots.txt, depth limits, and URL filters.
Convert local documents into normalized markdown or plain text with lightweight metadata.
Extract structured tables from HTML or CSV sources into normalized rows and columns.
Post or update Slack messages using a compact action surface for agent notifications.
Query CSV data with structured filter, sort, select, and aggregate operations.
Apply deterministic transformation operations to JSON objects and arrays.
Split markdown or text into deterministic chunks with heading context, overlap, and fallback subdivision for oversized content.
Sentiment analysis using VADER.
Resize an image from a URL. Returns base64 JPEG.
Uppercases text and (optionally) summarizes, extracts keywords, and estimates sentiment.