Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

introducing Campus. a collaborative, spatial workspace. your agents and teammates. shared memory. shared context. nothing resets. 400 commits in the last several dozen hours. we haven't been able to stop. demo coming. this is before that. a Campus you never graduate from. comment "CAMPUS" for first access.

Abel Mengistu

1,625 subscribers

481,623 views • 4 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

49 Comments

Andrew Daniels 💜4 months ago

@TondeHarsh Bro if this is stuff you demoing before FFDC — dang y’all going to kill this new wave of software development.

Abel Mengistu4 months ago

@TondeHarsh tune in my guy. tune in

Kathank Raithatha | DevRel4 months ago

Can't wait to try this 😍😍😍

prashant dalai4 months ago

Excited again 😍.

Abel Mengistu4 months ago

@prashantrdalai yea boiii

Decklabs4 months ago

how does the shared memory stay consistent when agents and humans edit the same space at the same time

Vladimir Gusev4 months ago

This changes how teams build together.

Abel Mengistu4 months ago

100%

Yeabkal4 months ago

CAMPUS

Jordan Bleek4 months ago

we literally just ran into this last week

Abel Mengistu4 months ago

20 terminal tabs was the breaking point 😂

Jordan Bleek4 months ago

we literally just ran into this last week

Pankaj Yadav4 months ago

Shared memory + shared context for agents and teammates? This is the future of collaborative AI dev. No more lost context, no more re-explaining everything. This is genius.

Jay (Soroush) Zare4 months ago

CAMPUS

BEE LAW 🐝👩🏽‍⚖️4 months ago

🤯🔥 this is about to change the game fr fr. i can see so many use cases!

Abel Mengistu4 months ago

@bossassbee_ it's honestly crazy. we've been plugged in

Glenford Williams 🇯🇲4 months ago

CAMPUS

0xBasedApe4 months ago

campus looks next level. shared memory that never resets? this changes everything.

Jity Woldemichael4 months ago

CAMPUS!!

행벅4 months ago

와, 400 커밋이라니 엄청나네요! 저도 얼리 액세스 꼭 참여해보고 싶어요.

Abel Mengistu4 months ago

👍

Vivek Yadav #PROCoach4 months ago

CAMPUS 100x

Nuisance4 months ago

One need a very BIG HUGE MONITOR 4This Nice

Abel Mengistu4 months ago

lol. pan and zoom my friend. we can browse the whole world with these two on a map.

Nuisance4 months ago

True Good Times To B Alive i think there some aliens somewhere bringing new ideas humans never thought off Ai Next Will have As s 4butt

Jorge Coca 🐶💙🦄4 months ago

CAMPUS

Abel Mengistu3 months ago

Thanks for the interest @jcocaramos! DM me, will send you a link

BARAKA KILEO4 months ago

CAMPUS

Jimmy Ashcot4 months ago

shared nothing context nothing resets is the dream but does it work

Abel Mengistu4 months ago

yes

Imad Bouirmane4 months ago

Cool CAMPUS

Shubham Sharma | AI & Tech4 months ago

we literally just ran into this last week

Abel Mengistu4 months ago

yes

Leo Amos4 months ago

Game changer 🔥🔥

Dals4 months ago

campus

Rodriq4 months ago

CAMPUS

'thedigitalpro'4 months ago

Oh go on then CAMPUS

Karol Gost4 months ago

CAMPUS

Aditya Shinde4 months ago

FlutterFlow is back again, guys 😉 Campus looks crazy!

Abel Mengistu4 months ago

it’s the most fun we’ve had working together

Timo Kruse4 months ago

CAMPUS

Yonas Beshawred4 months ago

🔥🔥🔥

Maker4 months ago

CAMPUS

Zelda4 months ago

Microsoft did it first.

Abel Mengistu4 months ago

wut

翼くん歌手を目指してます‼️｢let's 翼voice｣4 months ago

進化を感じますね⚖️ 情報が共有できるのは素晴らしいですが、過負荷になるかも。本当に注意が必要です。

Aura❄️4 months ago

How sill shared memory handle conflicting edits at scale?

Riya Malhotra2 months ago

never graduating sold me

Gustavo4 months ago

that “nothing resets” vibe is wild, low‑key wanna see the sync chaosw

Related Videos

we're live on Product Hunt 😸. Campus is the workspace where your project, agents, and team stay alive between sessions. a Campus you never graduate from. upvote here:

we're live on Product Hunt 😸. Campus is the workspace where your project, agents, and team stay alive between sessions. a Campus you never graduate from. upvote here:

FlutterFlow

163,415 views • 2 months ago

CANDACE LIED TO YOU! She has asserted multiple times that Tyler was never on campus! -Surveillance footage says that was a lie. Below are just a few quotes when Candace Owens has claimed Tyler was not on campus. She lied to you because you had to believe he wasn’t there so she could create an entirely new narrative involving the French Foreign Legion, Egyptian planes, US military, Ft Huachuca, Israel, TPUSA, Erika… the list goes on. • “Tyler has never even stepped foot on UVU campus.” (From her podcast episode “They Are Lying About Tyler Robinson” / Candace Ep 244. She added context that Robinson was accepted into Utah State University, not UVU, and questioned how he would know the campus and rooftop layout so well if he had never attended or visited.) • “Tyler Robinson maintains his innocence and has never even been to the UVU campus.” (Shared in posts and statements, including references to her investigation and sources. She emphasized there were “absolutely zero photos or video that the campus can produce to the contrary,” calling released images blurry and disputed by Robinson’s family.) • “He has never even stepped foot on the UVU campus… although she believes that he was around the campus on that day.” (Referenced in discussions of her claims, including a TikTok/video clip summarizing her position. She stressed he “never even stepped foot” while distinguishing that he may have been in the vicinity.) • “According to my source, Tyler has never even stepped foot on UVU campus… Curiously, however, my source says that Tyler Robinson was nearby the campus on that day.”

CANDACE LIED TO YOU! She has asserted multiple times that Tyler was never on campus! -Surveillance footage says that was a lie. Below are just a few quotes when Candace Owens has claimed Tyler was not on campus. She lied to you because you had to believe he wasn’t there so she could create an entirely new narrative involving the French Foreign Legion, Egyptian planes, US military, Ft Huachuca, Israel, TPUSA, Erika… the list goes on. • “Tyler has never even stepped foot on UVU campus.” (From her podcast episode “They Are Lying About Tyler Robinson” / Candace Ep 244. She added context that Robinson was accepted into Utah State University, not UVU, and questioned how he would know the campus and rooftop layout so well if he had never attended or visited.) • “Tyler Robinson maintains his innocence and has never even been to the UVU campus.” (Shared in posts and statements, including references to her investigation and sources. She emphasized there were “absolutely zero photos or video that the campus can produce to the contrary,” calling released images blurry and disputed by Robinson’s family.) • “He has never even stepped foot on the UVU campus… although she believes that he was around the campus on that day.” (Referenced in discussions of her claims, including a TikTok/video clip summarizing her position. She stressed he “never even stepped foot” while distinguishing that he may have been in the vicinity.) • “According to my source, Tyler has never even stepped foot on UVU campus… Curiously, however, my source says that Tyler Robinson was nearby the campus on that day.”

Paramount Tactical - Gary Melton

23,258 views • 5 months ago

Introducing Dex: the self-driving workspace for operators. Dex is the first agent system with full operational context and a self-updating knowledge base. Every datapoint from your workspace is ingested, synced, and structured into compounding context for agents to take action. Comment "DEX" or tag ThirdLayer access. First 1,000 sign-ups get 7 days free. After, join our rolling waitlist. Sign up at joindex [dot] com for a fun surprise. How dex works (threads)

Introducing Dex: the self-driving workspace for operators. Dex is the first agent system with full operational context and a self-updating knowledge base. Every datapoint from your workspace is ingested, synced, and structured into compounding context for agents to take action. Comment "DEX" or tag ThirdLayer access. First 1,000 sign-ups get 7 days free. After, join our rolling waitlist. Sign up at joindex [dot] com for a fun surprise. How dex works (threads)

Regina Lin

71,418 views • 5 months ago

PROSECUTOR: "Were you able to determine at what time or times Mr. Robinson visited the UVU campus on September 10th?" AGENT HULL: "Yeah, we were able to establish that Mr. Robinson had been on campus approximately 4 times throughout the day, twice before the shooting. The time of the shooting and then, uh, after the shooting, later in the evening into the early hours of the 11th."

PROSECUTOR: "Were you able to determine at what time or times Mr. Robinson visited the UVU campus on September 10th?" AGENT HULL: "Yeah, we were able to establish that Mr. Robinson had been on campus approximately 4 times throughout the day, twice before the shooting. The time of the shooting and then, uh, after the shooting, later in the evening into the early hours of the 11th."

Andrew Kolvet

311,490 views • 2 months ago

Your portfolio just got a team of Wall Street analysts today 👏 A while back, a friend shared this idea of an AI analyst that's always monitoring your portfolio for insights, patterns, and behaviors. I haven't been able to get it out of my head since. I've been experimenting with different forms and UIs to build this exact thing out, and we've finally launched the first version of how we want to build agents at Rallies. Our new agents tool gives you access to 20+ agents that monitor your portfolio all day and send notes when something meaningful happens. Think of it like email, except the messages are coming from agents with access to a lot of financial data and your portfolio.

Your portfolio just got a team of Wall Street analysts today 👏 A while back, a friend shared this idea of an AI analyst that's always monitoring your portfolio for insights, patterns, and behaviors. I haven't been able to get it out of my head since. I've been experimenting with different forms and UIs to build this exact thing out, and we've finally launched the first version of how we want to build agents at Rallies. Our new agents tool gives you access to 20+ agents that monitor your portfolio all day and send notes when something meaningful happens. Think of it like email, except the messages are coming from agents with access to a lot of financial data and your portfolio.

Rallies

10,318 views • 5 months ago

Providence officials were allegedly receiving information from bystanders and witnesses of the Brown shooting, and had a WEEK to release it. Information is just NOW coming out that people have seen the killer before and after the shooting, yet officials did NOTHING. "For the first time, we're hearing from a custodian who says he was working on the Brown campus weeks before the shooting...he saw the shooting suspect more than a dozen times...looking in and out of classrooms and going into the bathroom. Something felt off, so he says he notified a third party security company there on campus 3 times, but NOTHING was done." This story gets more and more INFURIATING.

Providence officials were allegedly receiving information from bystanders and witnesses of the Brown shooting, and had a WEEK to release it. Information is just NOW coming out that people have seen the killer before and after the shooting, yet officials did NOTHING. "For the first time, we're hearing from a custodian who says he was working on the Brown campus weeks before the shooting...he saw the shooting suspect more than a dozen times...looking in and out of classrooms and going into the bathroom. Something felt off, so he says he notified a third party security company there on campus 3 times, but NOTHING was done." This story gets more and more INFURIATING.

DeVory Darkins

38,246 views • 9 months ago

If your agents are just personal helpers, you are still the bottleneck. We just introduced Workspaces: a new way for agents and humans to work together with shared skills and memories. Agents need the freedom to operate like real members of your team, invoking other agents and humans to get work done. Many agents + many humans in one shared workspace.

If your agents are just personal helpers, you are still the bottleneck. We just introduced Workspaces: a new way for agents and humans to work together with shared skills and memories. Agents need the freedom to operate like real members of your team, invoking other agents and humans to get work done. Many agents + many humans in one shared workspace.

Hyperagent

29,188 views • 13 days ago

We’ve been in private beta with a human + AI workspace similar to Buzz, with a few really important differences: (We previously built a company backed by Slack that sold to Atlassian, so we've been thinking about this problem for a while) - Agents reply by default unless you specifically flip to “team chat.” This feels 10x better than having to @ mention the agent every time. - It’s all in the cloud, with shared compute spread across a set of VMs. Way smoother onboarding, and yes, you can still connect your claude/codex subscriptions - You don’t create an army of agents. Number of agents is a vanity metric. Instead, you create shared computers, each one is a “space” where you define shared memory, connectors, skills, automations, etc. The Type agent pulls the appropriate context from the space where you have the conversation. - You can connect it to Slack to make it easy for your team to adopt and slowly move over rather than having to rip out Slack day 1. We’re working with a couple dozen forward thinking companies, who have told us “the whole team loves type”, “it’s the most used app on my computer”, and “type gives you superpowers” Here's a demo of how it works. Reply if you want to test it out!

We’ve been in private beta with a human + AI workspace similar to Buzz, with a few really important differences: (We previously built a company backed by Slack that sold to Atlassian, so we've been thinking about this problem for a while) - Agents reply by default unless you specifically flip to “team chat.” This feels 10x better than having to @ mention the agent every time. - It’s all in the cloud, with shared compute spread across a set of VMs. Way smoother onboarding, and yes, you can still connect your claude/codex subscriptions - You don’t create an army of agents. Number of agents is a vanity metric. Instead, you create shared computers, each one is a “space” where you define shared memory, connectors, skills, automations, etc. The Type agent pulls the appropriate context from the space where you have the conversation. - You can connect it to Slack to make it easy for your team to adopt and slowly move over rather than having to rip out Slack day 1. We’re working with a couple dozen forward thinking companies, who have told us “the whole team loves type”, “it’s the most used app on my computer”, and “type gives you superpowers” Here's a demo of how it works. Reply if you want to test it out!

Fletcher Richman

374,915 views • 1 month ago

Here is a 2 minute clip from my last Youtube video shared over a month ago. Spoiler alert- no numbers have been "lowered", nothing has changed from this clip. I highly recommend watching the clip below for context around the HTF idea, the 74k inval level, and for additional context to the last HTF chart I shared. You can find the full video on my youtube at:

Here is a 2 minute clip from my last Youtube video shared over a month ago. Spoiler alert- no numbers have been "lowered", nothing has changed from this clip. I highly recommend watching the clip below for context around the HTF idea, the 74k inval level, and for additional context to the last HTF chart I shared. You can find the full video on my youtube at:

CrediBULL Crypto

95,667 views • 1 year ago

We’re introducing Workspace Intelligence. With the advanced reasoning of Gemini, we're eliminating context silos across your Workspace apps. Think of it as a unified intelligence layer that works across Workspace. See how Workspace Intelligence connects the dots and lets AI do the heavy lifting for you in this demo. #GoogleCloudNext

We’re introducing Workspace Intelligence. With the advanced reasoning of Gemini, we're eliminating context silos across your Workspace apps. Think of it as a unified intelligence layer that works across Workspace. See how Workspace Intelligence connects the dots and lets AI do the heavy lifting for you in this demo. #GoogleCloudNext

Google Workspace

123,979 views • 5 months ago

At our campus in Khouribga, we received The Associated Press The Associated Press: the world's largest news agency! We are proud that such a prestigious agency is interested in our school and our city and is coming to meet us. Never before has a Moroccan school received so much attention 🙏:

At our campus in Khouribga, we received The Associated Press The Associated Press: the world's largest news agency! We are proud that such a prestigious agency is interested in our school and our city and is coming to meet us. Never before has a Moroccan school received so much attention 🙏:

1337 School

43,664 views • 3 years ago

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,180 views • 4 months ago

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

Ronin

15,071 views • 1 month ago

🚨Candace Owens' conspiracy slop is IMMEDIATELY EXPOSED on Day 1 of Tyler Robinson's preliminary hearing. Candace Owens, repeatedly the last nine months: "Tyler Robinson has never even set foot on UVU's campus." VS. Lead investigator, under oath today: "We were able to establish that Mr. Robinson had been on campus approximately four times throughout the day. Twice before the shooting, at the time of the shooting, and then again after the shooting, later that evening and into the early hours of the 11th."

🚨Candace Owens' conspiracy slop is IMMEDIATELY EXPOSED on Day 1 of Tyler Robinson's preliminary hearing. Candace Owens, repeatedly the last nine months: "Tyler Robinson has never even set foot on UVU's campus." VS. Lead investigator, under oath today: "We were able to establish that Mr. Robinson had been on campus approximately four times throughout the day. Twice before the shooting, at the time of the shooting, and then again after the shooting, later that evening and into the early hours of the 11th."

Nathan Livingstone (MilkBarTV)

257,675 views • 2 months ago