tmptrash / harvester
JavaScript library for "fuzzy" HTML data extraction based on templates
☆18Updated this week
Alternatives and similar repositories for harvester
Users that are interested in harvester are comparing it to the libraries listed below
Sorting:
- A powerful Google Maps review scraper that works in 2025. Extracts multi-language reviews with images, handles MongoDB integration, and b…☆24Updated last week
- Expose MCP tools for LLMs☆12Updated last month
- A simple social media posts scheduler.☆15Updated last week
- ☆29Updated 8 months ago
- Guide: from fragile multi-agent app to prod ready with orra - code and resources.☆12Updated last month
- 🔖a minimal bookmark manager☆12Updated last month
- A database migration tool that bridges the gap between ORM migration patterns and SQL-first workflows.☆16Updated 2 months ago
- A lightweight TypeScript AI toolkit for multiple platforms☆12Updated last week
- ☆22Updated 3 months ago
- TypeScript library for Google search scraping using http requests with proxy support, pagination, and regional customization. Built for w…☆35Updated 2 months ago
- MCP remote server for AI Engineer World's Fair 2025☆14Updated 3 weeks ago
- COBOL for serverless headless browsers☆25Updated 7 months ago
- A tiny, dependency-free, highly customizable and configurable, easy to use file input with some pretty sweet features.☆12Updated 2 months ago
- A lightweight Python utility that aggregates and exports comprehensive system information to JSON, specifically designed for feeding syst…☆12Updated last month
- AgentFence is an open-source platform for automatically testing AI agent security. It identifies vulnerabilities such as prompt injection…☆11Updated 2 months ago
- ☆11Updated last year
- Use GPTparser with your OpenAI API to scrape & parse files into structured JSON files.☆13Updated last year
- The LLM-powered function builder for TypeScript☆21Updated 8 months ago
- Lightweight cli coding agent☆28Updated this week
- Simple orchestration for EC2 spot containers☆20Updated 7 months ago
- Automated web scraping spider generation using Browser Use and LLMs. Streamline the creation of Playwright-based spiders with minimal man…☆66Updated last week
- Radiantloom Email Assist 7B is an email-assistant large language model fine-tuned from Zephyr-7B-Beta, over a custom-curated dataset of 1…☆14Updated last year
- Branch Out Your Conversations☆40Updated 3 months ago
- A self-improving application that analyzes its own codebase and suggests improvements through pull requests.☆14Updated 2 months ago
- The semantic layer for software engineering: Connect code to meaning, build on understanding☆21Updated 3 weeks ago
- An open-source web scraping tool that converts websites into markdown format. Featuring customizable options, LLM-based filtering, and an…☆27Updated 9 months ago
- Open-Source, Local, Pricvacy focused, LLM data gathering tool for your own Digital Twin☆16Updated 6 months ago
- Local LLM enabled Human terminal interaction made easy.☆13Updated 4 months ago
- EnvoyJS is a simple JavaScript framework for building AI agents.☆43Updated 2 months ago
- Crawling framework, RSS reader and parser☆27Updated this week