An open API service providing package, version and dependency metadata of many open source software ecosystems and registries.

npmjs.org "extraction" keyword

pdftomarkdown 0.1.5
Convert any PDF to clean markdown from the command line: npx pdftomarkdown file.pdf
5 versions - Latest release: about 1 month ago - 45 downloads last month - 1 maintainer
@sketchscreens/extractor 0.1.4
The agent-first extraction contract: the prompt + parse-signal guidance an agent uses to turn a c...
4 versions - Latest release: 4 months ago - 45 downloads last month - 1 stars on GitHub - 1 maintainer
@xberg-io/opencode-xberg 1.3.11 πŸ’°
Local document extraction: text, tables, metadata, images from 107 formats with optional OCR.
34 versions - Latest release: 4 days ago - 2.52 thousand downloads last month - 9,426 stars on GitHub - 1 maintainer
Top 1.4% on npmjs.org
textract 2.5.0
Extracting text from files of various type including html, pdf, doc, docx, xls, xlsx, csv, pptx, ...
46 versions - Latest release: over 7 years ago - 59 dependent packages - 228 dependent repositories - 72.1 thousand downloads last month - 1,692 stars on GitHub - 1 maintainer
crawlio 0.1.0
Typed web scraping SDK β€” scrape, map, crawl, and search over HTTP, with a pluggable renderer, CLI...
2 versions - Latest release: about 3 hours ago - 1 maintainer
@metreeca/gear 0.4.0
Job executor and shared services for @metreeca/gear.
6 versions - Latest release: about 3 hours ago - 250 downloads last month - 0 stars on GitHub - 1 maintainer
@metreeca/gear-gcp 0.4.0
Google Cloud service implementations for @metreeca/gear.
3 versions - Latest release: about 2 hours ago - 154 downloads last month - 0 stars on GitHub - 1 maintainer
n8n-nodes-2kw 7.3.2
n8n community node for the 2kw.ai platform (engineering name: Backbone)
102 versions - Latest release: about 3 hours ago - 10.2 thousand downloads last month - 1 stars on GitHub - 1 maintainer
extracto 0.1.0
Official TypeScript/JavaScript SDK for Extracto β€” turn any URL + a schema into validated, typed J...
1 version - Latest release: 4 months ago - 0 stars on GitHub - 1 maintainer
@fragmentoid/turbo-crawl 0.1.0
Turn any web page into structured JSON. Claude Code or Codex writes a reusable extraction templat...
2 versions - Latest release: 8 days ago - 0 stars on GitHub - 1 maintainer
openbrand 0.2.3
Extract brand assets (logos, colors, backdrops) from any website URL
6 versions - Latest release: 5 months ago - 29.8 thousand downloads last month - 800 stars on GitHub - 1 maintainer
@c4a/extract 0.7.73
Language-plugin framework and repository runner for Context code evidence
97 versions - Latest release: about 7 hours ago - 5.91 thousand downloads last month - 8 stars on GitHub - 1 maintainer
@c4a/extract-go 0.7.73
Go extraction plugin and structural index for Context
58 versions - Latest release: about 7 hours ago - 4.67 thousand downloads last month - 8 stars on GitHub - 1 maintainer
@vosjs/tween 0.8.3
Records a GSAP-dialect timeline into a structured, per-element tween IR (TweenSpec/TimelineDoc) f...
15 versions - Latest release: 18 days ago - 1.97 thousand downloads last month - 5 stars on GitHub - 1 maintainer
pdfmux-mcp 1.4.0 πŸ’°
MCP server for pdfmux β€” give AI agents reliable PDF reading. #2 on opendataloader-bench.
1 version - Latest release: 7 months ago - 62 downloads last month - 83 stars on GitHub - 1 maintainer
@animus-ui/unplugin 0.1.62
Animus transform host for non-plugin bundlers β€” unplugin-based rollup/esbuild/rspack/webpack entr...
44 versions - Latest release: about 11 hours ago - 3.65 thousand downloads last month - 9 stars on GitHub - 1 maintainer
@animus-ui/cli 0.1.62
Standalone Animus extraction CLI β€” one-shot builds and artifact emission for any build system
45 versions - Latest release: about 11 hours ago - 3.82 thousand downloads last month - 9 stars on GitHub - 1 maintainer
decant-core 1.17.1 πŸ’°
A shared web extraction layer for AI conversations and regular web pages.
30 versions - Latest release: about 13 hours ago - 3.1 thousand downloads last month - 7 stars on GitHub - 1 maintainer
@pendral/docuflow 0.1.0
Official TypeScript SDK and CLI for DocuFlow: document intake, extraction and review, live events...
2 versions - Latest release: about 14 hours ago - 5 maintainers
@eigenpal/cli 0.20.58
Eigenpal CLI β€” author and run document workflows from your terminal. Agent-ready.
206 versions - Latest release: about 14 hours ago - 9.13 thousand downloads last month - 2 stars on GitHub - 1 maintainer
Top 4.1% on npmjs.org
deeks 3.2.1
Retrieve all keys and nested keys from objects and arrays of objects.
36 versions - Latest release: 5 months ago - 5 dependent packages - 574 dependent repositories - 7.25 million downloads last month - 8 stars on GitHub - 1 maintainer
@alexdee2007/deeks 2.3.0
Retrieve all keys and nested keys from objects and arrays of objects.
1 version - Latest release: almost 6 years ago - 2 dependent packages - 51 downloads last month - 8 stars on GitHub - 1 maintainer
question-kit 0.3.0
The standard library for System One models, starting with Jev: ready-made methods built by measur...
4 versions - Latest release: about 18 hours ago - 314 downloads last month - 4 stars on GitHub - 1 maintainer
website-profile-extractor 0.1.0
Fetch a website and use an LLM to extract structured profile data against a user-supplied schema....
1 version - Latest release: 5 months ago - 11 downloads last month - 0 stars on GitHub - 1 maintainer
fetchary 2.0.3 πŸ’°
Extract what matters. Semantic web extraction for Node.js and the command line, with optional bro...
13 versions - Latest release: about 23 hours ago - 748 downloads last month - 4 stars on GitHub - 1 maintainer
@postalsys/email-content 0.1.14
Extract conversationally relevant content from arbitrary email messages
19 versions - Latest release: 3 days ago - 2.16 thousand downloads last month - 1 maintainer
extract-youtube 1.0.510 πŸ’°
Fast, no-browser serverless-optimized YouTube transcript extractor, with optional cloud-ytdl audi...
510 versions - Latest release: 1 day ago - 33.3 thousand downloads last month - 77 stars on GitHub - 1 maintainer
@generaltranslation/vue-extractor 0.1.21
Vue source code extraction for General Translation
25 versions - Latest release: 5 days ago - 262 thousand downloads last month - 1,070 stars on GitHub - 3 maintainers
@generaltranslation/python-extractor 0.2.62
Python source code extraction for General Translation
77 versions - Latest release: 5 days ago - 516 thousand downloads last month - 1,070 stars on GitHub - 3 maintainers
@molecule/api-ai-document-extraction 1.0.2
Upload document β†’ extract text β†’ AI extract structured fields
3 versions - Latest release: 29 days ago - 465 downloads last month - 44 stars on GitHub - 1 maintainer
receipt-ocr-ng 1.4.4
AI‑powered receipt OCR for Nigerian fintech transactions (Opay, PalmPay, Kuda, etc.) – extracts s...
5 versions - Latest release: 2 months ago - 0 stars on GitHub - 1 maintainer
stealth-scraper 0.1.0
Official TypeScript/JavaScript SDK for Stealth Scraper β€” anti-bot-resistant web scraping API.
1 version - Latest release: 5 months ago - 1 maintainer
@justcrawl/sdk 0.3.0
The official TypeScript SDK for the JustCrawl scraping orchestration API
4 versions - Latest release: 1 day ago - 379 downloads last month - 0 stars on GitHub - 1 maintainer
ids-le-mcp 1.2.1
Extract every UUID, ULID, NanoID, ObjectId and Snowflake, and decode the time inside.
4 versions - Latest release: 1 day ago - 606 downloads last month - 1 stars on GitHub - 1 maintainer
ips-le-mcp 1.1.0
Extract every IP address, CIDR block and MAC, normalized and classified by scope.
3 versions - Latest release: 12 days ago - 602 downloads last month - 1 stars on GitHub - 1 maintainer
@laddhaanshul/content-renderer-core 1.0.7
Platform-agnostic parsing, extraction, sanitization and transformation engine for HTML, JSON, XML...
4 versions - Latest release: 5 months ago - 0 stars on GitHub - 1 maintainer
@ahmedtariq/skillforge 0.1.1 deprecated
Compile scattered company knowledge β€” Slack, Notion, GitHub, post-mortems β€” into Claude Agent Ski...
2 versions - Latest release: 6 months ago - 47 downloads last month - 0 stars on GitHub - 1 maintainer
@skforge/cli 0.1.0
Compile scattered company knowledge β€” Slack, Notion, GitHub, post-mortems β€” into Claude Agent Ski...
1 version - Latest release: 6 months ago - 0 stars on GitHub - 1 maintainer
@arch-engine/adapter-yarn-pnp 0.1.0
Safe, package.json-shape-based workspace topology extraction adapter for Yarn Berry / Plug'n'Play...
1 version - Latest release: 5 months ago - 0 stars on GitHub - 1 maintainer
@arch-engine/adapter-pnpm 0.1.1
Deterministic workspace topology extraction adapter for pnpm-managed monorepos.
2 versions - Latest release: 5 months ago - 0 stars on GitHub - 1 maintainer
paths-le 2.6.0
Find every path in a codebase and report whether it still points at anything.
4 versions - Latest release: 1 day ago - 1 stars on GitHub - 1 maintainer
paths-le-mcp 2.4.1
Extract file and directory paths from config files and code, with their kind and position.
10 versions - Latest release: 8 days ago - 1.42 thousand downloads last month - 1 stars on GitHub - 1 maintainer
dates-le-mcp 2.5.0
Extract dates and timestamps from logs, data files and code, with their format and position.
10 versions - Latest release: 12 days ago - 1.38 thousand downloads last month - 1 stars on GitHub - 1 maintainer
@edwinfom/resume-intel 0.2.1
LLM-first resume parsing infrastructure. Agnostic, structured, production-ready.
8 versions - Latest release: 5 months ago - 0 stars on GitHub - 1 maintainer
Top 7.1% on npmjs.org
crittr 5.0.0 πŸ’°
Crittr is a high performance critical css extraction library with a multiple url support.
23 versions - Latest release: 4 months ago - 2 dependent packages - 3 dependent repositories - 1.16 thousand downloads last month - 55 stars on GitHub - 1 maintainer
@paniniapi/extract 0.2.0
Statement extraction for Indian banking documents β€” CSV/Excel layouts, PDF text-layer, bank SMS, ...
2 versions - Latest release: 1 day ago - 1 stars on GitHub - 1 maintainer
@ohm_studio/sdk-core 0.10.1
Shared core for @ohm/sdk and @ohm/sdk-react-native β€” http client, types, errors, retry, streaming...
15 versions - Latest release: 5 months ago - 144 downloads last month - 0 stars on GitHub - 2 maintainers
@ohm_studio/sdk 0.12.0
OHM Studio SDK for JavaScript / TypeScript / React. Voice-to-structured-JSON clinical extraction ...
15 versions - Latest release: 5 months ago - 715 downloads last month - 0 stars on GitHub - 2 maintainers
@ohm_studio/sdk-react-native 0.12.0
OHM Studio SDK for React Native. Voice-to-structured-JSON clinical extraction APIs in your mobile...
15 versions - Latest release: 5 months ago - 0 stars on GitHub - 2 maintainers
string-le-mcp 2.7.0
Extract string values from config files, data files and plain text.
13 versions - Latest release: 1 day ago - 1.61 thousand downloads last month - 1 stars on GitHub - 1 maintainer
units-le-mcp 1.1.0
Extract durations, sizes, percentages and frequencies in one base unit, refusing ambiguous ones.
4 versions - Latest release: 12 days ago - 750 downloads last month - 1 stars on GitHub - 1 maintainer
urls-le-mcp 2.4.0
MCP server that extracts URLs from documentation, config and code β€” the engine behind the URLs-LE...
10 versions - Latest release: 12 days ago - 1.19 thousand downloads last month - 1 stars on GitHub - 1 maintainer
@synapt-dev/extract 0.6.1
SynaptExtraction IL v1 -- schema, validation, and finalization
11 versions - Latest release: 3 months ago - 0 stars on GitHub - 1 maintainer
@thelol3882/lexen 0.3.1
Config-driven translation extraction, validation, and sorting for next-intl, react-i18next, and f...
2 versions - Latest release: about 2 months ago - 0 stars on GitHub - 1 maintainer
@autumnice/agent-crawl 0.1.1
AI-assisted browser crawling CLI for structured extraction and file export
2 versions - Latest release: 5 months ago - 1 maintainer
@flyrank/dna 1.1.1
The All-In One Brand DNA Identity Extraction Toolbox SDK
26 versions - Latest release: 4 months ago - 2 stars on GitHub - 1 maintainer
ddna-tools 0.4.3
Reference implementation for .ddna envelope specification - extraction, sealing, and verification...
4 versions - Latest release: 2 months ago - 0 stars on GitHub - 1 maintainer
units-le 1.2.1
Find every quantity in a codebase, a number welded to a unit: durations, byte sizes, percentages ...
2 versions - Latest release: 1 day ago - 1 stars on GitHub - 1 maintainer
strings-le 2.7.0
Get every string value out of a codebase and into one place a person can read.
4 versions - Latest release: 1 day ago - 1 stars on GitHub - 1 maintainer
@memo-labs/ai-services 0.7.0
AI services (LLM client, embedding, extraction) for Memo SDK
6 versions - Latest release: 5 months ago - 110 downloads last month - 1 maintainer
@poldex/mcp-server 0.0.3
MCP server exposing PolDex commercial insurance extraction tools to AI agents
3 versions - Latest release: 6 months ago - 1 maintainer
llmbic 1.8.0
Hybrid data extraction β€” deterministic rules + LLM fallback, with per-field confidence scoring.
9 versions - Latest release: 5 months ago - 581 downloads last month - 0 stars on GitHub - 1 maintainer
agentic-doc-parse-and-extract-cli 1.11.0-beta.1
Official CLI for Laiye ADP (Agentic Document Processing) - document parsing and intelligent extra...
3 versions - Latest release: 6 months ago - 18 downloads last month - 10 stars on GitHub - 1 maintainer
@laiye-adp/agentic-doc-parse-and-extract-cli 1.11.0
Official CLI for Laiye ADP (Agentic Document Processing) - document parsing and intelligent extra...
13 versions - Latest release: 4 months ago - 70 downloads last month - 10 stars on GitHub - 2 maintainers
@multiplist/mcp-server 1.0.0
IP Vault with Citations β€” extract decisions, frameworks, and insights from AI conversations with ...
3 versions - Latest release: 6 months ago - 41 downloads last month - 0 stars on GitHub - 1 maintainer
trustcalljs 0.3.0
Utilities for validated tool calling and extraction with retries using LLMs - TypeScript port of ...
10 versions - Latest release: 7 months ago - 926 downloads last month - 0 stars on GitHub - 1 maintainer
@stalia/sdk 0.0.1
Reserved for Stalia (https://stalia.io). Bank statement extraction API. Public release coming soon.
1 version - Latest release: 6 months ago - 1 maintainer
@razroo/iso-facts 0.1.0
Deterministic fact materialization for AI-agent workflows: extract, query, verify, and check prov...
1 version - Latest release: 6 months ago - 11 stars on GitHub - 1 maintainer
edgeparse 0.2.3
High-performance PDF extraction β€” Rust engine, Node.js interface
5 versions - Latest release: 7 months ago - 2.7 thousand downloads last month - 149 stars on GitHub - 1 maintainer
edgeparse-wasm 0.2.5
EdgeParse PDF parser β€” WebAssembly build for browsers
2 versions - Latest release: 6 months ago - 134 downloads last month - 149 stars on GitHub - 1 maintainer
@nachoretro/internetsearch 1.1.2
Enhanced web search and content extraction MCP - search engines, RSS, YouTube transcripts, metada...
4 versions - Latest release: 6 months ago - 0 stars on GitHub - 1 maintainer
@openanonymity/nanomem 0.1.3
LLM-driven personal memory with agentic retrieval, extraction, and compaction
4 versions - Latest release: 6 months ago - 30 downloads last month - 49 stars on GitHub - 2 maintainers
feedstock 0.5.0
High-performance web crawler and scraper for TypeScript, powered by Bun and Playwright
11 versions - Latest release: 6 months ago - 106 downloads last month - 15 stars on GitHub - 1 maintainer
pdftables-io 0.1.0
Official JavaScript/TypeScript SDK for the pdftables.io API – extract tables from PDFs.
1 version - Latest release: 6 months ago - 0 stars on GitHub - 1 maintainer
numbers-le-mcp 2.5.0
Extract numeric values from config files, data files and plain text.
10 versions - Latest release: 12 days ago - 1.42 thousand downloads last month - 1 stars on GitHub - 1 maintainer
@opemcode/pdf-ai-extractor 1.0.1
Extract structured JSON from PDFs and images using OpenAI, with OCR fallback
2 versions - Latest release: 6 months ago - 19 downloads last month - 1 maintainer
@t3x-dev/core 0.0.4 removed
T3X Core - Deterministic semantic extraction, diff, and merge engine
4 versions - Latest release: 7 months ago - 0 downloads last month - 9 stars on GitHub - 1 maintainer
@peac/capture-core 0.16.4 πŸ’°
Runtime-neutral capture pipeline for PEAC interaction evidence
49 versions - Latest release: 2 months ago - 98 downloads last month - 14 stars on GitHub - 1 maintainer
designmaxxing 0.1.2
Pixel-perfect UI reverse engineering toolkit β€” extract design tokens, components, and layout from...
3 versions - Latest release: 7 months ago - 8 downloads last month - 0 stars on GitHub - 1 maintainer
@yolk-sdk/extractors 0.1.0-canary.116
Bounded text extraction for PDF, DOCX, XLSX, PPTX, and text files: an Effect FileExtractor servic...
19 versions - Latest release: 2 days ago - 1.44 thousand downloads last month - 0 stars on GitHub - 1 maintainer
n8n-nodes-shopgraph 1.0.1
n8n community node for product data extraction with per-field confidence scoring and extraction p...
2 versions - Latest release: 6 months ago - 1 maintainer
@arch-engine/adapter-monorepo 1.3.1
Federation-ready architecture extraction adapter for resolving workspace topologies deterministic...
9 versions - Latest release: 5 months ago - 736 downloads last month - 0 stars on GitHub - 1 maintainer
@nutrient-sdk/openclaw-nutrient-pdf 2026.6.3
Explicit Nutrient-powered PDF extraction tool and CLI for OpenClaw. Adds an on-demand nutrient_pd...
6 versions - Latest release: 4 months ago - 2 stars on GitHub - 5 maintainers
uplo-sidecar 0.2.0
Make your documents AI-ready. Scans folders, extracts structured data, generates .sidecar.md comp...
2 versions - Latest release: 7 months ago - 0 stars on GitHub - 1 maintainer
vue-harvest 0.0.4
Extract reusable component libraries and design tokens from any Vue application
4 versions - Latest release: 7 months ago - 0 stars on GitHub - 1 maintainer
@anumiti/netra-node 2.1.0
Official Node.js/TypeScript SDK for Anumiti NETRA β€” India's AI document intelligence API
7 versions - Latest release: 6 months ago - 258 downloads last month - 1 maintainer
algomath-extract 1.0.17
AlgoMath Framework - Transform AI assistants into reliable mathematical problem-solving environments
17 versions - Latest release: 7 months ago - 1 maintainer
@fluenti/cli 0.6.3
Fluenti CLI β€” message extraction from Vue SFC & TSX, PO/JSON catalog compilation
21 versions - Latest release: 7 months ago - 117 downloads last month - 5 stars on GitHub - 1 maintainer
extraktr 1.0.4
CLI for extracting tasks, decisions, and risks from conversations
5 versions - Latest release: 7 months ago - 3 stars on GitHub - 1 maintainer
apapyr 1.0.0
Extract structured data from invoices, receipts, and documents. PDF/image in, JSON out.
1 version - Latest release: 7 months ago - 1 maintainer
@ontosdk/core 0.1.2
Shared HTML→Markdown cleaning + AIO scoring engine. Powers @ontosdk/next, the Onto Read API, and ...
3 versions - Latest release: 3 days ago - 146 downloads last month - 1 maintainer
mails-skills 1.5.1
Email skills for AI agents β€” Claude Code, OpenClaw, Cursor. One command to give your agent an ema...
3 versions - Latest release: 7 months ago - 314 downloads last month - 1 stars on GitHub - 1 maintainer
@mcp-b/smart-dom-reader 6.0.3
Token-efficient DOM extraction for AI agents - Extract interactive elements, semantic structure, ...
57 versions - Latest release: 5 days ago - 1.76 thousand downloads last month - 104 stars on GitHub - 2 maintainers
@knowledgesdk/mcp 0.2.10
Official KnowledgeSDK Model Context Protocol Server - AI assistant integration for web knowledge ...
2 versions - Latest release: 7 months ago - 0 stars on GitHub - 1 maintainer
@hasna/crawl 0.4.20 deprecated
AI-powered web crawler β€” self-hosted Firecrawl alternative. Crawl, extract, render JS, search. CL...
24 versions - Latest release: about 2 months ago - 730 downloads last month - 0 stars on GitHub - 1 maintainer
cook-extract 0.0.1
Structured data extraction CLI for generic PDF documents via LLMs
1 version - Latest release: 7 months ago - 0 stars on GitHub - 1 maintainer
@knowledgine/core 0.7.0
Core library for extracting structured knowledge from markdown files
18 versions - Latest release: 6 months ago - 42 downloads last month - 3 stars on GitHub - 1 maintainer
structureai 1.0.0
Extract structured JSON from messy text using AI. Supports receipts, invoices, emails, resumes, c...
1 version - Latest release: 8 months ago - 8 downloads last month - 0 stars on GitHub - 1 maintainer
@hanivanrizky/nestjs-html-parser 2.3.1
⚠️ ARCHIVED - This package is no longer maintained. Please migrate to @hanivanrizky/nestjs-xpath-...
33 versions - Latest release: 9 months ago - 44 downloads last month - 0 stars on GitHub - 1 maintainer
betteringest 0.1.1
Zero-dependency CLI to bulk-ingest files into a knowledge graph. Chat-aware chunking, LLM extract...
2 versions - Latest release: 8 months ago - 24 downloads last month - 1 maintainer