Загрузка видео...

Не удалось загрузить видео

На главную

Introducing Omnara: the open-source alternative to Claude Managed Agents. Omnara is an API for creating and interacting with production-grade agents. You build the agent. Omnara handles hosting, durable state, sandboxes, permissions, secrets, and the rest of the production infrastructure. Available now

93,539 просмотров • 2 месяцев назад •via X (Twitter)

Комментарии: 56

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

Sign up and build your first agent at Or have your coding agent do it. Paste this into Claude Code, Codex, or whatever you use: Read this skill and use Omnara to build me an agent: First make sure I'm logged in to Omnara, then ask what I want to build and suggest a few example ideas.

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

Your agent works on whatever machines you give it: our hosted sandboxes, your own sandbox provider, or anything running the Omnara daemon (your laptop, a VM, a box in your VPC). Model Providers: Anthropic, OpenAI, Bedrock, OpenRouter. Or any other compatible endpoint. Open-source models welcome. Bring your own keys or use managed credits. Want all of it in your own environment? Self-host the whole thing:

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

A few agents we've built on Omnara: — scans X daily for buying signals and DMs us the leads — writes our product usage report every morning on a cron — sits in Slack as a teammate and picks up whatever we tag it on — reviews PRs against our codebase's conventions — handles customer support, under your brand Source for the first two:

Фото профиля Asher Dale
Asher Dale2 месяцев назад

Next level stuff 🔥🔥🔥

Фото профиля Kartik
Kartik2 месяцев назад

First stop along the way to a country of geniuses in a data center

Фото профиля Mehul Fanawala
Mehul Fanawala2 месяцев назад

Congratulations on the launch Ishaan. 🥳 Going to explore this.

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

🥳

Фото профиля Nikhil Prabhu
Nikhil Prabhu2 месяцев назад

lets go hyped

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

hyped! lets build!

Фото профиля Joshua wong
Joshua wong2 месяцев назад

pointed my agent at this and it told me it finally found a manager worth working for

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

AGI??

Фото профиля Christian Sparks
Christian Sparks2 месяцев назад

🚀🚀🚀

Фото профиля Christopher Jones
Christopher Jones2 месяцев назад

🔥 🔥🔥

Фото профиля Elias Stråvik
Elias Stråvik2 месяцев назад

@never_settles_ super cool - huge congrats on the launch! how should one think about omnara vs. vercel + eve agents? when should one pick one or the other?

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

hey thanks! good question. tldr: eve, like mastra, is a framework for building agents with code. you author one agent as a typescript codebase and ship it as a deployment. omnara is an api for running agents as a service: each agent is a durable object with endpoints for launching and steering it at runtime. wrote more here:

Фото профиля Elias Stråvik
Elias Stråvik2 месяцев назад

@never_settles_ amazing! read up on that thread but still don’t feel like i quite get it. i think even more examples of omnara in use would help - do you have a page with case studies or something? would love to learn more!

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

that's fair. the way i'd think about it: a lot of companies are building internal agent platforms right now, stripe minions, ramp inspect, shopify aquifer. each one is a service with endpoints their teams call to launch and interact with agents. omnara is that, open source. eve, mastra, langchain are for writing an agent in code and deploying it statically afterwards. omnara is a hosted service that you can create and interact with agents on. a platform. the docs walk through the api with worked examples:

Фото профиля Elias Stråvik
Elias Stråvik2 месяцев назад

@never_settles_ love it - will read up more in the docs as well, thanks a ton!

Фото профиля Vatsalpandya333
Vatsalpandya3332 месяцев назад

Lfggg!!

Фото профиля Angel Onuoha
Angel Onuoha2 месяцев назад

Great launch, lets go!

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

LG!!

Фото профиля Tom Greenwald
Tom Greenwald2 месяцев назад

Let's go Omnara 🚀

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

LG 🚀

Фото профиля FlowOps Daily
FlowOps Daily2 месяцев назад

open source shows up clearly in the Ishaan Sehgal Introducing Om part, and the presentation is clean.

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

thanks! have @Hinson_Kwong to thank

Фото профиля Anshul Jain
Anshul Jain2 месяцев назад

Been using the new platform for 2 weeks and it's one of the best AI infrastructures I've seen. Just pointed Claude at the docs and building new agents is super easy :)

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

awesome thats the goal :)

Фото профиля Aoden Teo
Aoden Teo2 месяцев назад

Awesome work. Beyond just being open source, I think not having your managed agents be linked to a model provider is the move.

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

agree! own your agents

Фото профиля Sadok
Sadok2 месяцев назад

Building the agent is the easy part compared to the infra

Фото профиля Divam Gupta
Divam Gupta2 месяцев назад

This is so cool!

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

hype 🙌

Фото профиля Saurabh Jambure
Saurabh Jambure2 месяцев назад

All the best 🚀

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

🚀

Фото профиля Chu You Chia
Chu You Chia2 месяцев назад

Been playing around with this, looks pretty cool. Gotta do some more extensive testing and report Looks like it will dramatically reduce deployment friction and infra complexity

Фото профиля Hinson Kwong
Hinson Kwong2 месяцев назад

This is huge let’s go!

Фото профиля Rohan Mukherjee
Rohan Mukherjee2 месяцев назад

congrats on the launch!

Фото профиля Sam Brickman
Sam Brickman2 месяцев назад

🔥🔥🔥🔥🔥

Фото профиля Vik Makarskyy
Vik Makarskyy2 месяцев назад

Incredible work, gold standard for managing intelligence.

Фото профиля Justin Schroeder
Justin Schroeder2 месяцев назад

congrats!

Фото профиля Chris Ife
Chris Ife2 месяцев назад

@ycombinator Congratulations on your launch 🚀

Фото профиля dnu
dnu2 месяцев назад

Open sourcing the hosting layer is a generous choice. It gives teams a way to inspect how long-running agents are managed instead of trusting a black box.

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

big fans of open source!

Фото профиля Pierson Marks
Pierson Marks2 месяцев назад

Congrats on the launch 🚀

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

thanks! 🚀

Фото профиля Ofek Shaked | AI Engineer
Ofek Shaked | AI Engineer2 месяцев назад

Durable state and sandboxes are the actual product. Permissions and secret handling is where these platforms usually leak first.

Фото профиля Aaron Makelky
Aaron Makelky2 месяцев назад

sick video edit!

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

thanks! @Hinson_Kwong

Фото профиля Samrith Shankar
Samrith Shankar2 месяцев назад

this is cool - internally we do the same at @withmitra, where the team can build agents directly using the MCP and the API

Фото профиля Dhruv Patel
Dhruv Patel2 месяцев назад

Amazing. Congrats on the launch 🚀

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

appreciate 🚀

Фото профиля Cryptpal Singh | 🍊
Cryptpal Singh | 🍊2 месяцев назад

lfg!

Фото профиля Ishaan Sehgal
Ishaan Sehgal2 месяцев назад

LFG!

Фото профиля Anders Lie
Anders Lie2 месяцев назад

The time to own your agents is nigh 🤖

Фото профиля boussecsou.x
boussecsou.x2 месяцев назад

I'm lovin'it

Фото профиля aditya
aditya2 месяцев назад

lfgggggg

Похожие видео

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

Dan Shipper

66,921 просмотров • 6 месяцев назад