正在加载视频...

视频加载失败

Ardent (Ardent) let's you clone any Postgres DB <6s at TB scale so coding agents can test their code and engineering teams can ship fast without fear of taking down production. It's already being used by dozens of teams like Supermemory and Surface Labs with 10TB+ of data across...

229,393 次观看 • 4 个月前 •via X (Twitter)

35 条评论

burak emre 的头像
burak emre4 个月前

@ArdentAI For those who are looking for an open-source version of it, check out

Vikram 的头像
Vikram4 个月前

@ArdentAI If you want to check it out :)

Colton 的头像
Colton4 个月前

@ArdentAI Is this actually faster than the copy on write cloning that postgres now _natively_ supports?

Hang Huang 的头像
Hang Huang4 个月前

@ArdentAI seems like we could get a partnership going @insforge 👀 YC 🤝 YC

Over/Under Market Intelligence 的头像
Over/Under Market Intelligence4 个月前

@ArdentAI The Postgres crash is a real fear. This is exciting!

Dev K 的头像
Dev K4 个月前

@ArdentAI fear of breaking production is the silent tax. 😐 coding agents need real data to test against. mocks lie. this is the infrastructure that makes agentic dev actually safe. so far one of the kind tool for agentic work.

Film By Adnan 的头像
Film By Adnan4 个月前

@ArdentAI Thanks for trusting us to produce this video!! 🫂

Max Williamson 的头像
Max Williamson4 个月前

@ArdentAI That is a great idea

Alex Bodner 的头像
Alex Bodner4 个月前

@ArdentAI what about data privacy?

adi 的头像
adi4 个月前

@ArdentAI congrats!

Rhoads 的头像
Rhoads4 个月前

@ArdentAI this is a good idea

Isaac Tolley 的头像
Isaac Tolley4 个月前

@ArdentAI incredible product and founder 🐐

Adarsh 的头像
Adarsh4 个月前

@ArdentAI This is a real problem. Great job @vchennai2

Satya Patel 的头像
Satya Patel4 个月前

@ArdentAI LET'S GOOOOO

Mike Hodara 的头像
Mike Hodara4 个月前

@ArdentAI I took more time writing this tweet than you replicating my db

Priyesh Srivastava 的头像
Priyesh Srivastava4 个月前

@ArdentAI @vchennai2 github app still has your name instead of Ardent. Please fix.

Leo 的头像
Leo4 个月前

@avimakesrobots @ArdentAI Let’s goooo

Srinivas Devaki 的头像
Srinivas Devaki4 个月前

@ArdentAI this is going to be incredible

Kartik Budholiya 的头像
Kartik Budholiya4 个月前

9 seconds. That’s literally how long it took one Claude agent to wipe out an entire company’s production Postgres DB + backups recently 😭 Ardent just made that nightmare optional. <6s clones of *any* Postgres DB at TB scale? Full isolated branches with real data for agents & devs? One CLI command, zero extra infra? This is the missing safety rail for agentic coding to actually ship at scale. No more mocks lying to you. No more “just don’t touch prod” prayers. Huge for anyone building with AI devs. Congrats @vchennai2 @ArdentAI @ycombinator — perfectly timed 🔥

Raphaël Dabadie 的头像
Raphaël Dabadie4 个月前

@ArdentAI Dope product !

synabun.ai 的头像
synabun.ai4 个月前

@ArdentAI Agents need real schema to do good work. Mocks lie. The hard part was always giving them production data without the blast radius. Sub-6s clone makes that a non-decision.

Mitch Radhuber 的头像
Mitch Radhuber4 个月前

@ArdentAI let’s go! 👏👏 absolutely necessary if you’re building anything remotely data-intensive

Connex 的头像
Connex4 个月前

@ArdentAI I can see this being the standard for RLDF (Reinforcement Learning from Database Feedback). You run an agent in a high-fidelity clone, validate the state change, and only then commit to prod. This is how we move from 'Chatbots' to actual 'Autonomous Engineers.' Massive congrats

Imran Sayed 的头像
Imran Sayed4 个月前

@ArdentAI The best dev tools remove the fear from doing normal work at serious scale.

Alec 的头像
Alec4 个月前

@ArdentAI Lfg Vikram!

Schmoop 的头像
Schmoop4 个月前

@ArdentAI Buy a @NetApp . They've been doing this with every db for 20+ years. If you clone 6tb db 5x you'll destroy your storage. Think about it

Shreyas 的头像
Shreyas4 个月前

@ArdentAI How about you can let your AI agent access the Postgres DB directly? lets you do that

Aditi.py 的头像
Aditi.py4 个月前

@ArdentAI Wait isn’t this non-compliant. Having a copy of customer prod data on your laptop? What if some npm package compromises your laptop data

Startup & Tech 的头像
Startup & Tech4 个月前

@ArdentAI Cloning a 10TB Postgres DB in under 6 seconds is actually wild. Most engineering teams spend hours just setting up staging environments or fixing broken pipelines. If this works as promised, it solves a massive bottleneck for teams using coding agents at scale.

Mohamed Khalif 的头像
Mohamed Khalif4 个月前

@ArdentAI Great stuff

Voodoochild92 的头像
Voodoochild924 个月前

@ArdentAI A bit confused why even bother building this!?!?? I did this with Claude code when I gave it access to our read only about four months ago.

Shashank 的头像
Shashank4 个月前

@ArdentAI been using production and staging database all this while. now, i can copy the data while my AI is still x-high thinking

Sudip 的头像
Sudip4 个月前

@ArdentAI Congratulations @vchennai2 on the launch

Dmitry S 的头像
Dmitry S4 个月前

@ArdentAI why would you clone/branch a db? why would you give *write* access to your clankers? can't they vibecode an ORM?

Adam Patarino 的头像
Adam Patarino4 个月前

@ArdentAI Ayy congrats @vchennai2!

相关视频

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Fraction AI

67,899 次观看 • 1 年前

Most AI assistants can now generate impressive responses. Very few can actually move work forward. At Glean, we’ve been focused on a different question: what would it take for every employee to have an expert, agentic coworker that understands their business, their role, and their day—and can safely take action across it? Today we’re introducing the latest generation of Glean Assistant: a Work AI partner grounded in your enterprise context with new capabilities like: • Real-time voice, so people can talk to Assistant like a colleague. Get briefed on an account on the way to a meeting, ask follow-up questions, and line up next steps without touching a keyboard. • On-brand slide generation and in canvas, so teams can go from an idea and a few source docs to a polished, brand-aligned deck or message in minutes. • Agent sandboxes and 100+ enterprise actions, so Assistant can analyze large datasets and coordinate work across tools like Salesforce, Jira, Confluence, GitHub, Google Calendar, Asana, and Canva—helping teams move directly from insight to execution, with guardrails in place. • Visible, editable personal graph and proactive agents, so every employee can see and control the context Assistant uses to plan their day, surface action items, and summarize what they accomplished each week. Customers are already seeing nearly two hours saved per employee per day because their teams can quickly surface the right information, generate what they need, and move work forward without breaking focus. We’ll be sharing what this looks like in practice at Glean:LIVE – Context in Action today at 10 AM PT. I’d love for you to join us. Watch here:

Arvind Jain

15,524 次观看 • 7 个月前