
Learn the workflows
Scrape a forum, pipe it to GPT or Claude Code, ship a monitoring agent. Real workflows on real actors — the operator's playbook.
Read the playbook
Scraping · Apify · AI social listening
Turn the Asian forums global tools ignore into sentiment you can actually read.
How it works
Three steps — the same pipeline behind every tool and tutorial on this site.
PTT, LIHKG, Bahamut, HardwareZone — public posts, no login, through battle-tested Apify actors.
Pipe it to GPT or Claude — sentiment, share-of-voice, and what people are actually saying.
Schedule it. When volume spikes or the mood flips, you hear about it — not a week later.
Where to start

Scrape a forum, pipe it to GPT or Claude Code, ship a monitoring agent. Real workflows on real actors — the operator's playbook.
Read the playbook
Forum sentiment, HK property, cost calculator — instant answers, no login. Pip does the fetching.
Try a tool
Scheduled monitors, cross-forum share-of-voice, sentiment exports. The turnkey dashboard that never sleeps.
See Pro monitoringFree tools
Topics
Threads, replies and site-wide search from LIHKG and HKGolden.
Hong Kong property dataEstate transactions, sale and rental listings, and the CCL index.
Singapore forumsBoard listings, threads and replies from HardwareZone, EDMW included.
Taiwan forumsPosts, push comments and replies from PTT, Mobile01 and Bahamut.
Southeast Asia forumsSearch, topics and comments from Pantip (Thailand) and VOZ (Vietnam).
Korean forumsBoard listings, full posts and comments from theqoo (Korea).
Latest guides
Centaline publishes no official API. Wire Apify's official MCP server into Claude Code or Claude Desktop instead, and you can ask in plain English how Taikoo Shing's current asking prices compare with its recent deals — Claude calls centaline-scraper itself and does the math. We ran it for real: 33 transactions against 40 listings, for about $0.17.
2026-10-12 A practical guide to using TypeSafe's Jev API for sentiment, relevance and intent labels on forum posts: the HTTP request shape, a 7-step recipe with the measured evidence behind each step, the full question definitions we used, cost per 100,000 posts, rate limits and pitfalls.
2026-10-12 We ran TypeSafe's Jev (jev-1.13.0) and Claude Haiku 5.5 on the same sentiment, relevance and intent questions over 405 real forum posts from LIHKG, Pantip and HardwareZone. Haiku led by 3 to 5 points on 150 held-out Cantonese posts; Jev cost less than half as much, answered in about 0.36 seconds, and its confidence scores were well calibrated.
Every tutorial is written from actually running the pipelines — not from theory.
Who's behind this →