hmhngx
bce8f736cc
Migrates the anthropic branch of generateListName (site #4 of 9, issue set_list_name tool. - Appends setListNameTool to server/src/sdk/anthropicTools.ts. - This is the only one of the 9 sites converting a free-text completion (not a JSON-shaped one) into a structured tool call - the prompt previously asked for bare text like "Product Listings", not JSON. - Unlike sites #1-3, this branch does NOT early-return: the shared tail here is pure string post-processing (quote-strip, first-line-only, length validation, Title-Case) with no JSON.parse, so it works identically whether it receives raw text (ollama/openai) or decision.listName (anthropic). Assigning `llmResponse = decision.listName` and falling through to the unchanged shared tail is the smaller, more faithful port than duplicating that logic inline would have been. - max_tokens bumped 20 -> 80 for the anthropic branch only (ollama/openai untouched). The prior budget was sized for bare-text output with zero JSON overhead; a {"listName": "..."} tool call needs headroom on top of a name that can legally run up to 50 chars per the existing validation. Left uncorrected, this would risk stop_reason: max_tokens truncation on longer names, converting what worked before into a guaranteed "List 1" fallback for exactly the names most likely to need one. - temperature 0.1 preserved as before. Verified: full project tsc --noEmit clean. Mocked runtime check (ts-node) covered 7 scenarios: clean valid name, quote-wrapped name correctly stripped, multi-line response correctly truncated to its first line, an empty name correctly throws internally and falls back to "List 1" via the EXISTING (llmResponse || '').trim() guard - unchanged, no new guard code needed - an undefined listName field degrades through that same existing guard identically, an oversized (>50 char) name correctly throws and falls back, and a thrown helper error (e.g. simulated truncation) falls back identically. Also asserted opts.maxTokens === 80 specifically, to catch any regression of the budget bump.
Turn Any Website Into A Structured API
✨ The unified open-source no-code platform for real-time web scraping, crawling, search and AI data extraction ✨
Go To App •
Documentation •
Website •
Discord •
Watch Tutorials
Sponsors
|
|
IPcookIPcook provides 55M+ real residential IPs across 185+ countries and regions, delivering fast and reliable proxy solutions for web scraping, automation, and data collection. 99.99% uptime, average response times under 0.5s, and 100,000 concurrency at max. Start with a FREE 100MB Trial to experience IPcook’s proxy service.
|
|
|
NodemavenThe most reliable proxy provider for web scrapping with the Highest Quality IP on the market. Why Nodemaven?
Discount Code: |
|
|
NovadaNovada provides high-quality residential proxies and a powerful Scraper API for reliable web data collection at scale. Access real residential IPs worldwide, reduce blocks, and collect the data your scraping workflows need.
|
|
|
CoreClawCoreClaw — Production-ready Web Data APIs for AI agents and developers. Extract structured data from the web and build powerful automation workflows.
|
|
|
TestMu AITestMu AI is the Native AI-Agentic Cloud Platform to Supercharge Quality Engineering. Test Intelligently and Ship Faster. |
What is Maxun?
Maxun is an open-source no-code web data platform for turning the web into structured, reliable data. It supports extraction, crawling, scraping, and search — designed to scale from simple use cases to complex, automated workflows.
Ecosystem
-
Extract – Emulate real user behavior and collect structured data from any website.
- Recorder Mode – Record your actions as you browse; Maxun turns them into a reusable extraction robot.
- AI Mode – Describe what you want in natural language and let LLM-powered extraction do the rest.
-
Scrape – Convert full webpages into clean Markdown or HTML and capture screenshots.
-
Crawl – Crawl entire websites and extract content from every relevant page, with full control over scope and discovery.
-
Search – Run automated web searches to discover or scrape results, with support for time-based filters.
-
SDK – A complete developer toolkit for scraping, extraction, scheduling, and end-to-end data automation.
-
CLI – Create robots, trigger runs, and retrieve extracted data from your terminal.
How Does It Work?
Maxun robots are automated tools that help you collect data from websites without writing any code. Think of them as your personal web assistants that can navigate websites, extract information, and organize data just like you would manually - but faster and more efficiently.
There are four types of robots, each designed for a different job.
1. Extract
Extract emulates real user behavior and captures structured data.
- Recorder Mode - Record your actions as you browse; Maxun turns them into a reusable extraction robot.
Example: Extract 10 Property Listings from Airbnb
https://github.com/user-attachments/assets/recorder-mode-demo-video
- AI Mode - Describe what you want in natural language and let LLM-powered extraction do the rest.
Example: Extract Names, Rating & Duration of Top 50 Movies from IMDb
https://github.com/user-attachments/assets/f714e860-58d6-44ed-bbcd-c9374b629384
Learn more here.
2. Scrape
Scrape converts full webpages into clean Markdown, HTML and can capture screenshots. Ideal for AI workflows, agents, and document processing.
Learn more here.
3. Crawl
Crawl entire websites and extract content from every relevant page, with full control over scope and discovery.
Learn more here.
4. Search
Run automated web searches to discover or scrape results, with support for time-based filters.
Learn more here.
Quick Start
Getting Started
The simplest & fastest way to get started is to use the hosted version: https://app.maxun.dev.
Installation
Maxun can run locally with or without Docker
Upgrading & Self Hosting
- Self Host Maxun With Docker
- Upgrade Maxun With Docker Compose Setup
- Upgrade Maxun Without Docker Compose Setup
Features
- ✨ Extract Data With No-Code – Point and click interface
- ✨ LLM-Powered Extraction – Describe what you want; use LLMs to scrape structured data
- ✨ Developer SDK – Programmatic extraction, scheduling, and robot management
- ✨ Handle Pagination & Scrolling – Automatic navigation
- ✨ Run Robots On Schedules – Set it and forget it
- ✨ Turn Websites to APIs – RESTful endpoints from any site
- ✨ Turn Websites to Spreadsheets – Direct data export to Google Sheets & Airtable
- ✨ Adapt To Website Layout Changes – Auto-recovery from site updates
- ✨ Extract Behind Login – Handle authentication seamlessly
- ✨ Integrations – Connect with your favorite tools
- ✨ MCP Support – Model Context Protocol integration
- ✨ LLM-Ready Data – Clean Markdown for AI applications
- ✨ Self-Hostable – Full control over your infrastructure
- ✨ Open Source – Transparent and community-driven
Demos
Maxun can be used for various use-cases, including lead generation, market research, content aggregation and more. View demos here: https://www.maxun.dev/usecases
License
This project is licensed under AGPLv3.
Project Values
We believe in fair and responsible use of open source. If you rely on this project commercially, please consider contributing back or supporting its development.
Support Us
Star the repository, contribute if you love what we’re building, or sponsor us.
Contributors
Thank you to the combined efforts of everyone who contributes!