正在加载视频...
视频加载失败
New: Readwise for OpenClaw🦞 Save anything with one click from your browser or phone: articles, tweets, books, youtube, podcasts, newsletters, more. Your claw now has instant access to that full library as markdown. Easily search and actually stay on top of it all.
35 条评论

Installation instructions here: Or just jump straight to the clawhub skill: npx clawhub install readwise-official

This, of course, is powered by our CLI which we announced last week: Looking for an MCP? we have that too:

@openclaw This is the second time in a month where yinz have just built the same thing I was planning to. Extremely appreciative of the product selection!

@openclaw Woah.

@openclaw Funny, i've been trying to do this well in other ways. Good feature!

@davemorin @openclaw This is much better that my implementation (API + Obsidian + Skill) Thanks!!

@openclaw your ai agent now knows everything you've ever read, that's lowkey terrifying and useful at the same time

@openclaw The knowledge gap is real. Running 8 agents through @openclaw — the biggest friction wasn't orchestration or scheduling. It was giving agents access to what I'd actually read, saved, and curated. Markdown-native is the right format. Agents don't need a UI. They need the signal.

@openclaw this solves the biggest issue with local agents: lack of curated context. pushing bookmarks straight into agent memory is huge

@davemorin @openclaw Needed this, will be trying it out

@davemorin @openclaw Awesome! Let us know how it works for you :)

@davemorin @openclaw Will let you know what I think

@openclaw Keep cooking 🔥🔥

@openclaw ✍️🫡

@openclaw is it able to pull context from videos?

@openclaw It will save the full transcript of YouTube videos and podcasts! No transcripts for videos on X... yet

@openclaw 👏🏻👏🏻👏🏻 bravo team, this is awesome!

@BradGroux @openclaw How does it work with X? Does the user need an api?

@BradGroux @openclaw Nope, you don't need your own app! Just connect your Readwise account at and you'll be good to go.

@davemorin @openclaw I think I will resubscribe :) I really miss you guys product. Seems to be the right time to come back!

@davemorin @openclaw Awesome! Welcome back :)

@openclaw Does it also extract YouTube video transcript? X posts, threads, articles and media?

@openclaw Yup all of the above and more :)

@openclaw awesome migrating back immediately! How come you guys aren't suporting Instagram posts & reels? This and direct images/ videos are the last barriers for me preventing me from dropping mymind completely.

@openclaw On the roadmap! Instagram does not like content leaving their ecosystem and does not make it easy...

@openclaw Mymind figured it out guys, it should be possible. I have used scrapers like apify to get Instagram data and it has worked - inexpensive too Pls make it happen 🙏🙏🙏 then I can rely on reader being my only base to save everything

@openclaw Does it also work with Claude Code?

@openclaw Yes! Check out our CLI or MCP:

@openclaw WOW! THIS IS A COMPLETE GAME-CHANGER. I WILL HAVE TO TRY THIS OUT!

@openclaw Verification of agent understanding matters as much as the content itself.

@openclaw This is a big unlock: “agent + personal knowledge base” works best when ingestion is 1-click + everything normalizes to markdown. Next step is relevance+recency ranking so the claw doesn’t drown in your backlog.

@openclaw openclaw looks like such a clean way to bridge the gap between static content and agentic workflows. are you guys planning to integrate this more deeply into the reader app for automatic tagging or summaries?

@openclaw We already have automatic tagging and summaries but... yes, we are building a "global chat" feature that should be agentic and able to do a lot of this stuff your claw can do!

@openclaw I have given my Readwise API key to my openclaw to retrieve my highlights, process them the way I want and add them, alongside more insights from current conversations and analysis of the topic at hand to Obsidian. Should I change to this?

@openclaw If you give your openclaw the readwise cli, it will be able to do all that, but also have some more powerful tools such as semantic search over all of your saved data! But if you're happy with your process, no need to change it! The API is great too :)



