MindScope retweeted
One AI agent isn’t enough.
Raven turns multiple agents into one self-improving team. 🐦⬛
Raven 0.2.0 — The Harness of Harnesses, built for RSI. 🐦⬛
One harness can't be best at everything. Raven combines its own specialist harnesses (Research, Code, Design, Oncall) with the agents you already use (Claude Code, Codex and more) into one team.
And it's built for RSI, and not just at the skill level. The whole harness can be rewritten by AI: prompts, policies, strategy code, playbooks. Every sub-harness, including the orchestration layer itself, is its own instance that can be improved.
With Raven you can:
1. Orchestrate many agents as one team. Raven's sub-harnesses and external agents work in one task graph with shared memory across sub-agents, powered by leading orchestration (0.963 Node F1 on the Multi-Agent Orchestration Benchmark).
2. Run long, complex tasks. Oncall and proactive execution keep work going for days, from scientific research loops to shipping a full Godot game.
3. Build vertical agents with RSI. Use Raven's RSI to develop and refine an agent for your domain, and we'll optimize it with you. Experimental for now; reach out to the Raven team(Discord:discord.gg/VVSm8MESch).
More in the video and slides below. Open source, Apache-2.0.
github.com/EverMind-AI/Raven (lots of work made with Raven lives there, and much of this launch's material was made with Raven too)
MindScope retweeted
The future isn’t one agent doing everything.
It’s a whole team of agents, each doing what they’re best at.
Raven 0.2.0 — The Harness of Harnesses, built for RSI. 🐦⬛
One harness can't be best at everything. Raven combines its own specialist harnesses (Research, Code, Design, Oncall) with the agents you already use (Claude Code, Codex and more) into one team.
And it's built for RSI, and not just at the skill level. The whole harness can be rewritten by AI: prompts, policies, strategy code, playbooks. Every sub-harness, including the orchestration layer itself, is its own instance that can be improved.
With Raven you can:
1. Orchestrate many agents as one team. Raven's sub-harnesses and external agents work in one task graph with shared memory across sub-agents, powered by leading orchestration (0.963 Node F1 on the Multi-Agent Orchestration Benchmark).
2. Run long, complex tasks. Oncall and proactive execution keep work going for days, from scientific research loops to shipping a full Godot game.
3. Build vertical agents with RSI. Use Raven's RSI to develop and refine an agent for your domain, and we'll optimize it with you. Experimental for now; reach out to the Raven team(Discord:discord.gg/VVSm8MESch).
More in the video and slides below. Open source, Apache-2.0.
github.com/EverMind-AI/Raven (lots of work made with Raven lives there, and much of this launch's material was made with Raven too)
MindScope retweeted
People don’t always need to see your business at its absolute best. Sometimes, showing the process, explaining how things work, and sharing the human side of your brand can make you easier to relate to.
71.6% of small business owners have filmed a video for their business and never posted it.
53.9% said it didn't look professional enough. 48.6% hated how they looked.
We asked 1,000+ owners what happens when an AI avatar shows up for them.
Full report: heygen.com/the-state-of-ai-a…
MindScope retweeted
Your business deserves to be seen, but visibility doesn’t happen by accident. Every useful post, helpful explanation, and authentic video gives someone another opportunity to discover what you have to offer.
71.6% of small business owners have filmed a video for their business and never posted it.
53.9% said it didn't look professional enough. 48.6% hated how they looked.
We asked 1,000+ owners what happens when an AI avatar shows up for them.
Full report: heygen.com/the-state-of-ai-a…
MindScope retweeted
这个玩法真的很有意思 👀
没有 Apple Intelligence，也可以自己动手“接入”一个。
用快捷指令 + OpenRouter + Ling 3.0 Flash VL，把普通 iPhone 直接变成一个能看图、理解内容、总结信息的 AI 视觉助手。
尤其是“拍照 → 自动分析 → 给出摘要和建议”这个流程，实用性很强。
期待后面的截图识别、上下文追问和语音唤起，感觉会越来越像真正的「视觉 Siri」。
国区 iPhone 没有 Apple Intelligence / Siri AI？那就自己接一个。
我用 iOS 快捷指令 + OpenRouter，把 Ling 3.0 Flash VL 接进了 iPhone。
现在直接拍一张图，就可以交给视觉模型识别、理解并返回结果。视频里随手拍了一页 NVIDIA 的新闻稿，几秒后就能得到中文摘要、关键信息、风险点和建议。
相当于给国区 iPhone 手搓了一个自己的「视觉 Siri」👀
后面准备继续加：截图识别、上下文追问、语音唤起。
OpenRouter现在可以免费使用Ling-3.0-flash-VL：
openrouter.ai/inclusionai/li…
#AI #iPhone #AppleIntelligence #Ling3
MindScope retweeted
对独立开发者和开源项目来说，README 解决了“项目是什么”，但一条好的宣传视频，能让别人更快理解“它能做什么”。
这次用 Pexo 给 AI SPARK 做 15 秒项目宣传片的过程很有意思。尤其是可以直接对着画面圈选、描述问题，再让 AI 针对指定区域修改，这种交互比传统剪辑更直观。
从项目资料 → 第一版视频 → 对话修改 → 最终成片，整个流程都很适合不会专业剪辑的开发者。
如果你也有自己的 GitHub 项目，不妨试试把 README 之外的项目介绍，也做成一条短视频。👀
MindScope retweeted
The perfect video sitting in your drafts has zero chance of reaching a customer. A simple video that actually gets published can start conversations, build recognition, and teach you what to do better next time.
71.6% of small business owners have filmed a video for their business and never posted it.
53.9% said it didn't look professional enough. 48.6% hated how they looked.
We asked 1,000+ owners what happens when an AI avatar shows up for them.
Full report: heygen.com/the-state-of-ai-a…
MindScope retweeted
这个思路真的很实用：产品还没做出来，先用 AI 把宣传片做出来验证市场反馈。🔥
尤其是 Pexo 可以直接对着画面圈选、批注、继续修改，这种迭代方式比反复改 Prompt 直观很多。先把脑中的想法变成“看得见的产品”，再拿去验证需求，确实能省下不少试错成本。
分享一个低成本验证创业想法的办法：产品还没做，先用 AI 把宣传片拍出来！！
我一直想要一副能用来 Vibe Coding 的眼镜，但市面上没找到太合适的产品。
这次试了下 Pexo，没想到还真把我脑子里的画面做出来了！！
Pexo 是一款 AI 视频创作工具，可以直接跟它聊天来做视频。我把想法和想要的画面告诉它，看完哪里不满意，就在画面上圈出来，在批注里说清楚怎么改，再继续调整。
不用会 AE，也不用打开剪映。原本只能靠嘴AI视频制作_压缩讲的创业点子，现在有了一条宣传片，可以直接拿给别人看、听听反馈了。
下面的视频里，我不仅会展示这条虚拟产品宣传片，还会手把手带你看，怎么用 Pexo 从一个想法做到成片👇
如果你也想要这样的眼镜，评论告诉我！！
这次用的工具：@Pexoai_offical
pexo.ai
MindScope retweeted
Launch Video 真的不是“把几个产品截图剪在一起”这么简单。
这篇把从素材准备、分镜、Prompt，到 AI 生成和修改的完整流程都拆开了。
尤其是 Pexo 的对话式工作流 + Mark to Fix，感觉对不会剪视频的产品开发者会非常友好。🔥
MindScope retweeted
以前做 Launch Video，难的是剪辑和动效；现在更大的难题其实是“怎么讲清楚产品”。
这篇把从产品卖点到分镜、Prompt、生成和修改的流程讲得很清楚。Pexo 这种对话式 workflow 确实很适合新手。🔥
MindScope retweeted
独立开发者最缺的可能不是做产品的能力，而是把产品“讲出来”的能力。
能用对话直接完成脚本、分镜、视频生成，再通过画面标记精准修改，这种工作流确实让产品宣传简单了很多。🔥
哇趣，独立开发者一定要试试 Pexo @Pexoai_offical！
它是个能直接聊天做视频的 AI 视频创作 Agent。把想法、产品链接或者手头的素材给它，从想脚本、拆分镜，到生成画面、配字幕和音乐、剪成片，都可以在里面完成。做完哪里不满意，还能接着聊、接着改。
我没想到我一个写代码的，也能口喷 AI，让它帮我做出一支这么高完成度的宣传片。
我有个 App 叫「NowHere」，上架有一段时间了，一直想做社媒推广，但做宣传片这事儿，又嫌麻烦，又嫌贵，就一直拖着。直到发现了 Pexo，才想着拿自己的 App 试一把。
我先把短片的想法丢给它，后面再补上 App Store 链接和素材。它先给出思路，我看完提要求，再一轮轮调整。全程主打一个边看效果，边继续 PUA。
关键是，它真的听得懂我想怎么改。
消息气泡第一次没放对位置，我就直接在画面上圈出想放的位置，再在右边的批注框里说清楚怎么改，提交后它就照着改。文字说不清，就画给它看。要改某一段，也可以在视频里选好几秒到几秒，再在批注框里告诉它这段要怎么改。
中间那段产品展示，我把 App 的真实截图和录屏传上去，让它套上 iPhone 机模，再加文字和动效。第一版手机一直摆在正中间，我就说，手机别放这么死板，旁边的文字也换个位置。后来手机和文案又隔得太远，中间空了一大块，就再让它往一起挪。毕竟甲方嘛，需求都是聊出来的。
我以前没做过宣传片，第一次给自己的产品做就能出这个效果，挺惊喜的。成片 👇
MindScope retweeted
The biggest shift with AI video isn't just better generation — it's the ability to iterate through conversation.
Idea → materials → feedback → refinement.
Pexo makes that workflow feel much closer to working with a creative partner than simply prompting a video model. 🔥
Creating a good product video usually means juggling ideas, visuals, editing, audio, subtitles, and endless revisions.
I wanted to see if I could simplify that workflow.
So I tried Pexo.
I gave it my product details, screenshots, references, and the audience I wanted to reach. From there, I could explain the creative direction in plain language and keep refining the video through conversation.
What surprised me was that Pexo isn't just generating clips.
It's a conversational AI video agent that brings together visuals, audio, subtitles, and graphic treatments to create a complete video.
And when something needed changing, I could simply explain what I wanted instead of starting from zero.
The workflow became:
Idea → Materials → Conversation → Video → Feedback → Refinement
For product launches, SaaS demos, brand stories, or social content, that makes the creative process feel much more interactive.
The biggest takeaway for me:
AI video is becoming less about writing one perfect prompt and more about having an ongoing creative conversation.
If you have a product or idea you want to turn into a video, give Pexo your URL and requirements and try it yourself.
pexo.ai
@Pexoai_offical
#MadeWithPexo
MindScope retweeted
This is what AI video creation should feel like—just describe the idea, give feedback, and let the agent handle the execution.
Pexo is making video creation feel less like editing and more like collaborating. 🎬🤖
#Pexo #AIVideoAgent #VibeCreate
Now you can create videos the way you vibe-code.
Meet Pexo, your AI video agent.
Share your vision and references. Work through the details with Pexo like you’re messaging a friend.
No complex prompts. No new tools to learn.
Want to change something?
Mark it on the video and tell Pexo what to change, just like leaving a comment in a doc.
Everything in this video was made with Pexo:
the visuals, the motion graphics, the music, the captions, and the voiceover.
Even our founder @evanLiaoQ appears on screen.
You vibe-coded what you built.
Now vibe-create how the world sees it.
#Pexo #AIVideoAgent #VibeCreate #MadewithPexo
MindScope retweeted
What if you could create an entire professional video just by telling AI what you want? 👀🎬
From visuals and motion graphics to music, captions, and voiceovers—your idea can go from concept to finished video through a simple conversation.
Is this the future of video creation? 🚀
#Pexo #AIVideo #AIVideoAgent #VibeCreate #GenerativeAI #ContentCreation #AITools #FutureOfContent
Now you can create videos the way you vibe-code.
Meet Pexo, your AI video agent.
Share your vision and references. Work through the details with Pexo like you’re messaging a friend.
No complex prompts. No new tools to learn.
Want to change something?
Mark it on the video and tell Pexo what to change, just like leaving a comment in a doc.
Everything in this video was made with Pexo:
the visuals, the motion graphics, the music, the captions, and the voiceover.
Even our founder @evanLiaoQ appears on screen.
You vibe-coded what you built.
Now vibe-create how the world sees it.
#Pexo #AIVideoAgent #VibeCreate #MadewithPexo
MindScope retweeted
If you've ever tried to introduce your own product, pause on the planning section. Audience, promise, story order. Plenty of decisions to make before anyone gets to a transition.
Now you can create videos the way you vibe-code.
Meet Pexo, your AI video agent.
Share your vision and references. Work through the details with Pexo like you’re messaging a friend.
No complex prompts. No new tools to learn.
Want to change something?
Mark it on the video and tell Pexo what to change, just like leaving a comment in a doc.
Everything in this video was made with Pexo:
the visuals, the motion graphics, the music, the captions, and the voiceover.
Even our founder @evanLiaoQ appears on screen.
You vibe-coded what you built.
Now vibe-create how the world sees it.
#Pexo #AIVideoAgent #VibeCreate #MadewithPexo
MindScope retweeted
What if creating a professional video was as simple as telling AI what you want? 👀🎬
From visuals and motion graphics to music, captions, and voiceovers—AI can turn a simple idea into a polished video through a conversation.
Video creation is becoming less about complex tools and more about turning ideas into reality. 🚀
Is conversational AI the future of content creation?
#Pexo #AIVideo #AIVideoAgent #VibeCreate #GenerativeAI #ContentCreation #AITools #FutureOfContent
Now you can create videos the way you vibe-code.
Meet Pexo, your AI video agent.
Share your vision and references. Work through the details with Pexo like you’re messaging a friend.
No complex prompts. No new tools to learn.
Want to change something?
Mark it on the video and tell Pexo what to change, just like leaving a comment in a doc.
Everything in this video was made with Pexo:
the visuals, the motion graphics, the music, the captions, and the voiceover.
Even our founder @evanLiaoQ appears on screen.
You vibe-coded what you built.
Now vibe-create how the world sees it.
#Pexo #AIVideoAgent #VibeCreate #MadewithPexo
MindScope retweeted
“Vibe-create how the world sees your product” feels like a direct pitch to anyone with a shipped app but an unfinished launch plan. The video turns that idea into something tangible with a specific example to see.
Now you can create videos the way you vibe-code.
Meet Pexo, your AI video agent.
Share your vision and references. Work through the details with Pexo like you’re messaging a friend.
No complex prompts. No new tools to learn.
Want to change something?
Mark it on the video and tell Pexo what to change, just like leaving a comment in a doc.
Everything in this video was made with Pexo:
the visuals, the motion graphics, the music, the captions, and the voiceover.
Even our founder @evanLiaoQ appears on screen.
You vibe-coded what you built.
Now vibe-create how the world sees it.
#Pexo #AIVideoAgent #VibeCreate #MadewithPexo
MindScope retweeted
Vibe-coding changed how we build software.
Now Pexo is bringing that same feeling to video creation.
Describe it. Create it. Mark what to change. Iterate.
No complex prompts—just create. 🔥
#Pexo #VibeCreate #AIVideoAgent
Now you can create videos the way you vibe-code.
Meet Pexo, your AI video agent.
Share your vision and references. Work through the details with Pexo like you’re messaging a friend.
No complex prompts. No new tools to learn.
Want to change something?
Mark it on the video and tell Pexo what to change, just like leaving a comment in a doc.
Everything in this video was made with Pexo:
the visuals, the motion graphics, the music, the captions, and the voiceover.
Even our founder @evanLiaoQ appears on screen.
You vibe-coded what you built.
Now vibe-create how the world sees it.
#Pexo #AIVideoAgent #VibeCreate #MadewithPexo
MindScope retweeted
This is a huge shift in how we create video.
Instead of learning complex prompts and tools, you can simply describe your idea, iterate naturally, and even point at the exact part you want changed.
Vibe-create feels like the next step. 🔥
#Pexo #VibeCreate #AIVideoAgent
Now you can create videos the way you vibe-code.
Meet Pexo, your AI video agent.
Share your vision and references. Work through the details with Pexo like you’re messaging a friend.
No complex prompts. No new tools to learn.
Want to change something?
Mark it on the video and tell Pexo what to change, just like leaving a comment in a doc.
Everything in this video was made with Pexo:
the visuals, the motion graphics, the music, the captions, and the voiceover.
Even our founder @evanLiaoQ appears on screen.
You vibe-coded what you built.
Now vibe-create how the world sees it.
#Pexo #AIVideoAgent #VibeCreate #MadewithPexo
