English | 中文
An AI-powered digest that tracks the top builders in AI — researchers, founders, PMs, and engineers who are actually building things — and delivers curated summaries of what they're saying.
Philosophy: Follow people who build products and have original opinions, not influencers who regurgitate information.
A daily or weekly digest delivered to your preferred messaging app (Telegram, Discord, WhatsApp, etc.) with:
- Summaries of new podcast episodes from top AI podcasts
- Key posts and insights from 25 curated AI builders on X/Twitter
- Full articles from official AI company blogs (Anthropic Engineering, Claude Blog)
- Links to all original content
- Available in English, Chinese, or bilingual
- Install the skill in your agent (OpenClaw or Claude Code)
- Say "set up follow builders" or invoke
/follow-builders - The agent walks you through setup conversationally — no config files to edit
The agent will ask you:
- How often you want your digest (daily or weekly) and what time
- What language you prefer
- How you want it delivered (Telegram, email, or in-chat)
No API keys needed — all content is fetched centrally. Your first digest arrives immediately after setup.
Your delivery preferences are configurable through conversation. Just tell your agent:
- "Switch to weekly digests on Monday mornings"
- "Change language to Chinese"
- "Make the summaries shorter"
- "Show me my current settings"
The source list (builders and podcasts) is curated centrally and updates automatically — you always get the latest sources without doing anything.
The skill uses plain-English prompt files to control how content is summarized. You can customize them two ways:
Through conversation (recommended): Tell your agent what you want — "Make summaries more concise," "Focus on actionable insights," "Use a more casual tone." The agent updates the prompts for you.
Direct editing (power users):
Edit the files in the prompts/ folder:
summarize-podcast.md— how podcast episodes are summarizedsummarize-tweets.md— how X/Twitter posts are summarizedsummarize-blogs.md— how blog posts are summarizeddigest-intro.md— the overall digest format and tonetranslate.md— how English content is translated to Chinese
These are plain English instructions, not code. Changes take effect on the next digest.
- Latent Space
- Training Data
- No Priors
- Unsupervised Learning
- The MAD Podcast with Matt Turck
- AI & I by Every
Andrej Karpathy, Swyx, Josh Woodward, Kevin Weil, Peter Yang, Nan Yu, Madhu Guru, Amanda Askell, Cat Wu, Thariq, Google Labs, Amjad Masad, Guillermo Rauch, Alex Albert, Aaron Levie, Ryo Lu, Garry Tan, Matt Turck, Zara Zhang, Nikunj Kothari, Peter Steinberger, Dan Shipper, Aditya Agarwal, Sam Altman, Claude
- Anthropic Engineering — technical deep-dives from the Anthropic team
- Claude Blog — product announcements and updates from Claude
# From ClawhHub (coming soon)
clawhub install follow-builders
# Or manually
git clone https://github.com/zarazhangrui/follow-builders.git ~/skills/follow-builders
cd ~/skills/follow-builders/scripts && npm installgit clone https://github.com/zarazhangrui/follow-builders.git ~/.claude/skills/follow-builders
cd ~/.claude/skills/follow-builders/scripts && npm install- An AI agent (OpenClaw, Claude Code, or similar)
- Internet connection (to fetch the central feed)
That's it. No API keys needed. All content (blog articles + YouTube transcripts + X/Twitter posts) is fetched centrally and updated daily.
- A central feed is updated daily with the latest content from all sources (blog articles via web scraping, YouTube transcripts via Supadata, X/Twitter via official API)
- Your agent fetches the feed — one HTTP request, no API keys
- Your agent remixes the raw content into a digestible summary using your preferences
- The digest is delivered to your messaging app (or shown in-chat)
See examples/sample-digest.md for what the output looks like.
- No API keys are sent anywhere — all content is fetched centrally
- If you use Telegram/email delivery, those keys are stored locally in
~/.follow-builders/.env - The skill only reads public content (public blog posts, public YouTube videos, public X posts)
- Your configuration, preferences, and reading history stay on your machine
MIT