Cloudglue

Video context for your AI ☁️ Try Tinycloud, your AI agent for video work 👉 now open for beta:

[Kevin Dela Rosa @kdrwins]

Excited to be in San Jose this week for ACM @CAISconf ! I'll be presenting our recent work at the AgentSkills poster session:

📚Tool-Skills vs. Workflow-Skills: Routing and Composition in a Multimodal Agent Harness
🔗 https://t.co/ri5I2wwMKq

[Amy Xiao @amyxst]

https://t.co/ig8y3acP8s

[Tinycloud @iamtinycloud]

Tinycloud is in public beta ☁️

it's an AI agent for video work. point it at your videos and it sees everything: transcripts, audio, visual context, slides, speaker patterns, all of it.

ask it anything. or tell it what to build.

[Cloudglue @CloudglueDev]

It's official, Tinycloud is all grown up.

Follow its new X account for updates, edu content, and early looks at what's coming next.

👉 @iamtinycloud

[Cloudglue @CloudglueDev]

@amyxst @ericxtang @minhsmind 👀

[Cloudglue @CloudglueDev]

@ojusave @amyxst 🌥️🫶

[Amy Xiao @amyxst]

We just launched Tinycloud into public beta 🌥️

It’s an AI agent for video work. It sees everything in your videos (transcripts, audio, visual context, on-screen slides, speaker patterns, and more) so you can query and make artifacts from them.

Think Claude Code but for doing work across your videos.

Try it and show us what you create → https://t.co/dfKusQCKIY 🧵

[Cloudglue @CloudglueDev]

@rauchg @sonofalli @ceciaramitaro @MadsMcIlwain 🌉 We’ll be at Demo Day on April 16 in San Francisco.

[Cloudglue @CloudglueDev]

Cloudglue is in the 2026 Vercel AI Accelerator cohort. 🎉

Vercel just published the full cohort: 39 teams building the next wave of AI. We're proud to be among them.

What we're building: the context layer for video. Just like you wouldn't build your own database to power an app, you shouldn't have to build your own video understanding infrastructure. That's Cloudglue, so developers can ship video-enabled AI applications in hours, not months.

A lot is shipping in the next few weeks. Stay tuned.

Full cohort: https://t.co/oXoIcVwFgC

[Cloudglue @CloudglueDev]

Thanks @rauchg @sonofalli @ceciaramitaro @MadsMcIlwain for bringing together this group of builders. We’re grateful to be part of it.

[Gavin Ching @gching]

day 4/30 @OpenAI chat apps🚀

bring youtube content into chatgpt using @CloudglueDev and start analyzing any youtube vids in chatgpt ☁️

get insights like dialogue and empower your workflows with any video content 🤯

@CloudflareDev @RedwoodJS MCP UI makes this too easy 😇

[Cloudglue @CloudglueDev]

We out here at ICCV!
Thanks Kevin for bringing my face to 🌺 H a w a i i

[Kevin Dela Rosa @kdrwins]

Our little cloud guy made it to ICCV @CloudglueDev

[Daytona @daytonaio]

Yesterday we hosted our monthly AI Builders Meetup at the @datadoghq office in SF 🏙️
Full house again — amazing talks, live demos, great energy & networking! 🙌
Huge thanks to @datadoghq, our speakers & everyone who joined. Already excited for the next one! 🚀
@BraceSproul, @iddogino, @amyxst, @TomHacohen, @JukicVedran, @CipcicMarijan

[Gavin Ching @gching]

this is too good to not share for @interaction poke

i automated generating newsletter emails from youtube vids every week with these MCP:

getting latest youtube vids about @resend with @Linkup_platform and @perplexity_ai

@CloudglueDev to analyze the vids for poke

@resend to send off these emails

all done by poke every week for me.... im lazy now

#ResendMCPHackathon

[Cloudglue @CloudglueDev]

We're 🧑‍🍳

[yo puaaa 👋 @yo_puaaa]

Weekend project

Integrate Dropbox files into app.

Decent long weekend I would say

[yo puaaa 👋 @yo_puaaa]

before and after i solve a bug

[Cloudglue @CloudglueDev]

Ever since I was a young cloud ☁️🌞

[Cloudglue @CloudglueDev]

Woahh our first tutorial from the community
Love to see it @tyler_agg ! 🔥🔥🔥

[Tyler @tyler_agg]

I just made a walkthrough on how to turn any video library into a searchable, chat-ready AI tutor

it can:
– find answers instantly without scrubbing through hours of video
– show you the exact video & timestamp the answer came from
– understand what’s happening on-screen visually, not just the audio

reply “video” and I’ll DM you the walkthrough (must be following)

[Kevin Dela Rosa @kdrwins]

thanks to everyone who packed the room for my autonomous video hunter talk @ReconVillage , was a blast chatting with folks afterwards and hearing about your use cases. links in bio to video deep research agent repo; slides/vids soon. cheets

#defcon33 #defcon #OSINT #Ai