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.

1/ Introducing Kiro Crew. 👻 An open source, persistent development workspace that runs on your hardware and works wherever you are. It started as an internal tool called MeshClaw, shaped by hundreds of contributors across the company. Now it’s yours to build on too. Read the full story →

Kiro

22,070 subscribers

26,017 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

20 Comments

Kiro2 months ago

2/ Work from anywhere: start on the desktop app, web dashboard, or CLI. Continue in Slack, Discord, Telegram, Teams, Webex, WeCom, or WeChat. Context carries across all of them.

Kiro2 months ago

3/ It works when you don’t. Multi-step tasks execute unattended, recurring jobs run on your schedule, and heartbeats monitor your systems and deployments until something needs you.

Kiro2 months ago

4/ Multi-agent orchestration: run several conversations in parallel, or delegate work to subagents that report back. Nothing waits in line. Docs →

Kiro2 months ago

5/ Apps: purpose-built interfaces for work that doesn’t belong in chat. Issue Triage, Research Assistant, Agent Manager, and more, ship at launch, or build your own.

Kiro2 months ago

6/ Secure by design: 7-layer defense-in-depth, from OS-level sandboxing to signed audit logs. Because it’s open source, you can verify every layer yourself. GitHub →

Kiro2 months ago

7/ What would you offload first if it could run while you slept? Get started →

Nikhil Swaminathan2 months ago

Congrats! Looks interesting. First run though :(

Garry Collinz A2 months ago

It’s useless if we don’t have a good model to harness its power .. kiro should bring out a good coding plan for this

Nhan Tran2 months ago

All you need just release Fable

helvinho2 months ago

Congratulations on the launch, I'm looking forward to testing!

Vishal Alhat2 months ago

First thing I offloaded: a Node.js microservices migration. Kicked it off, went for chai, came back to 4 steps done and a clear failure report on step 5. Best part? Corrected it once about frontend checks. Never repeated myself again. Wrote it up here:

InvestingGenius2 months ago

booooriiiiiiing

Abhishek Tiwari2 months ago

When are you guys putting updated open models in the harness?

Rounit2 months ago

@kirodotdev On my Livestream I use this Daily. I recommend this to my viewers and they use it. I have 4.5k sub and gets good views on YT. YT:- rounieee If I can get a deal that would be great. DM me.

ʙ ᴀʟʟᴀɴ ᴡ ☧2 months ago

I love you all 💜🙏🏻

mc2 months ago

@grok how’s kiro crew ensuring that it remembers past decisions and enforces it to steer sessions? Will they benefit from using and

Jared Traehorn2 months ago

Context carrying across Slack, Discord, and CLI is the easy demo. The harder question is what it keeps versus quietly drops after week three of unattended runs, since that's usually where the useful state erodes.

AI Mastery Guide2 months ago

An internal tool turned open source workspace, that's a great story behind it

Генал1 month ago

Здравствуйте. Скажите, почему я не могу отправлять картинки через kiro?

maria zallocco2 months ago

Nice!

Related Videos

Excited to launch the mem0 Browser Extension. It’s an open-source, cross-LLM tool that lets you own your memories across ChatGPT, Claude, and Perplexity.

Excited to launch the mem0 Browser Extension. It’s an open-source, cross-LLM tool that lets you own your memories across ChatGPT, Claude, and Perplexity.

Taranjeet

37,883 views • 1 year ago

In an AI world, effort is no longer the bottleneck—ideas are. Open-source AI enables anyone to have access to build anything they want without depending on the one-sided gates that closed-source offers. This is amplified by the open innovation that open-source development enables.

In an AI world, effort is no longer the bottleneck—ideas are. Open-source AI enables anyone to have access to build anything they want without depending on the one-sided gates that closed-source offers. This is amplified by the open innovation that open-source development enables.

Sentient

17,408 views • 8 months ago

Introducing Mentat - an open source, GPT-4 powered coding assistant! Mentat runs in your command line, giving it the context of your projects and allowing it to coordinate edits across multiple files! More videos and a link to github below:

Introducing Mentat - an open source, GPT-4 powered coding assistant! Mentat runs in your command line, giving it the context of your projects and allowing it to coordinate edits across multiple files! More videos and a link to github below:

Scott Swingle

292,739 views • 3 years ago

Introducing Open Lovable v3 - an open source AI design engineer 🔥 Enter a URL and agents will create an on brand clone you can build on top of. Powered by Gemini 3 Pro and 's new branding format. Try out the 100% open source example, link below!

Developers Digest

178,287 views • 10 months ago

We'd like to remind everyone that @Dogecoin is an open-source project based on the code of #Bitcoin and that virtually all development of Dogecoin is done by volunteers. A small number of core developers & contributors also work here at the Dogecoin Foundation.

We'd like to remind everyone that @Dogecoin is an open-source project based on the code of #Bitcoin and that virtually all development of Dogecoin is done by volunteers. A small number of core developers & contributors also work here at the Dogecoin Foundation.

Dogecoin Foundation

247,134 views • 1 year ago

Introducing Lazy 2.0 — our AI that understands what you're working on and brings your past knowledge into the moment, in the blink of an eye — all with a single shortcut. It’s like talking to your past self — wherever you are on your desktop.

Introducing Lazy 2.0 — our AI that understands what you're working on and brings your past knowledge into the moment, in the blink of an eye — all with a single shortcut. It’s like talking to your past self — wherever you are on your desktop.

Ahmed Men ⌘

82,845 views • 1 year ago

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Tom Greenwald

48,528 views • 19 days ago

☁️ Introducing the Helicone AI Gateway, *now on the cloud* Pass-through billing. Bring your own key. 1 API 100+ models 0% markup 99% uptime And yes, it’s fully open source. Here’s how it works 👇

☁️ Introducing the Helicone AI Gateway, now on the cloud Pass-through billing. Bring your own key. 1 API 100+ models 0% markup 99% uptime And yes, it’s fully open source. Here’s how it works 👇

Justin Torre

35,228 views • 1 year ago

Our charts started as an extension of our coding agent that builds strategies for you As we scale into a larger charting platform, we're calling it Vela. Live at with a growing open source community at Vela. The best of Vela will always be in our hosted platform first: In today's update, Quant now works across your whole workspace. Set up every chart from one conversation. Live now.

Our charts started as an extension of our coding agent that builds strategies for you As we scale into a larger charting platform, we're calling it Vela. Live at with a growing open source community at Vela. The best of Vela will always be in our hosted platform first: In today's update, Quant now works across your whole workspace. Set up every chart from one conversation. Live now.

LuxAlgo

17,554 views • 5 days ago

What if instead of autoresearch reflecting incremental progress from a single person, it reflected *hundreds* of researchers’ progress, updated live, with every run’s data point being interactive and reproducible? You could survey the full space of explored ideas, see which changes actually move the benchmark, and fold the most promising ideas into your next run. Labless ( is my attempt at this. It can support thousands of simultaneous training runs across contributors around the world, each learning & improving together to hillclimb on a fixed benchmark, validated using a standardized codebase scaffold. Importantly, all valid training runs auto-submit to Labless, so failed experiments are as visible and reproducible as the successes. We have an agentic API that lets you or your coding agent study every run submitted so far so you don't waste time investigating something someone already tried, and you can source novel ideas from other contributors. Labless already hosts our Nanopath challenge to build the best pathology foundation model that trains in 1 hour on a single GPU. We are hoping to expand the platform further and support a suite of open-source research challenges. If this resonates with you, if you think the path to research innovation lies in open-source collaborative hill-climbing, please reach out.

What if instead of autoresearch reflecting incremental progress from a single person, it reflected hundreds of researchers’ progress, updated live, with every run’s data point being interactive and reproducible? You could survey the full space of explored ideas, see which changes actually move the benchmark, and fold the most promising ideas into your next run. Labless ( is my attempt at this. It can support thousands of simultaneous training runs across contributors around the world, each learning & improving together to hillclimb on a fixed benchmark, validated using a standardized codebase scaffold. Importantly, all valid training runs auto-submit to Labless, so failed experiments are as visible and reproducible as the successes. We have an agentic API that lets you or your coding agent study every run submitted so far so you don't waste time investigating something someone already tried, and you can source novel ideas from other contributors. Labless already hosts our Nanopath challenge to build the best pathology foundation model that trains in 1 hour on a single GPU. We are hoping to expand the platform further and support a suite of open-source research challenges. If this resonates with you, if you think the path to research innovation lies in open-source collaborative hill-climbing, please reach out.

Paul Scotti @ ICML

22,181 views • 3 months ago

THIS GUY UPDATED AN OPEN SOURCE TOOL FOR CLAUDE FABLE 5 THAT TAKES A SINGLE IMAGE AND AUTOMATICALLY REBUILDS IT AS A PREMIUM SCROLL LINKED WEB ANIMATION Instead of slicing videos by hand or exporting individual frames, you just hand it an image and it recreates the entire sequence as a pure scroll mapped experience - Pick an anchor image and set your overall creative direction - The tool automatically scales it into motion clips and uses ffmpeg to rip out every frame in the background - Maps the frames directly to your scroll position, tracking the cursor for an ultra smooth user experience - AND its open source, so you can drop the skill into your own terminal workspace He tested it on a highly detailed origami style travel website and it came out genuinely good for something built completely in one shot Turning a single photo into an automated frame mapped scrolling app is the kind of thing that used to take a developer hours

THIS GUY UPDATED AN OPEN SOURCE TOOL FOR CLAUDE FABLE 5 THAT TAKES A SINGLE IMAGE AND AUTOMATICALLY REBUILDS IT AS A PREMIUM SCROLL LINKED WEB ANIMATION Instead of slicing videos by hand or exporting individual frames, you just hand it an image and it recreates the entire sequence as a pure scroll mapped experience - Pick an anchor image and set your overall creative direction - The tool automatically scales it into motion clips and uses ffmpeg to rip out every frame in the background - Maps the frames directly to your scroll position, tracking the cursor for an ultra smooth user experience - AND its open source, so you can drop the skill into your own terminal workspace He tested it on a highly detailed origami style travel website and it came out genuinely good for something built completely in one shot Turning a single photo into an automated frame mapped scrolling app is the kind of thing that used to take a developer hours

0xMarioNawfal

112,087 views • 2 months ago

Introducing Supermemory - an AI hub for all your bookmarks and notes. content you consume often gets lost. put it in your second brain to make use of it. me and my friends have been working on this open source project for months now - but the story is actually crazy 🧵

Introducing Supermemory - an AI hub for all your bookmarks and notes. content you consume often gets lost. put it in your second brain to make use of it. me and my friends have been working on this open source project for months now - but the story is actually crazy 🧵

Dhravya Shah

73,249 views • 2 years ago

MausBot (MausBot) is a free, open-source chat app for a team of AI agents. It’s an open-source chat app for AI bots that runs locally on your machine, using the models you already have (Claude, Codex, Grok, and more). Your data stays on your computer. Heading towards superintelligence.

MausBot (MausBot) is a free, open-source chat app for a team of AI agents. It’s an open-source chat app for AI bots that runs locally on your machine, using the models you already have (Claude, Codex, Grok, and more). Your data stays on your computer. Heading towards superintelligence.

Omkar Satpute

21,705 views • 6 days ago

We are excited to announce that Pelagus Wallet ⛵ is an open-source browser extension wallet for use on Quai Network ⚡️💵. Read the full announcement of Pelagus Wallet on the Quai Website:

We are excited to announce that Pelagus Wallet ⛵ is an open-source browser extension wallet for use on Quai Network ⚡️💵. Read the full announcement of Pelagus Wallet on the Quai Website:

Pelagus Wallet ⛵

90,327 views • 3 years ago

Introducing Jitsu, the open source event data pipeline. Every signup, click and payment in your product is an event. Most companies ship those off to a vendor and pay by the event to read them back. We run the same job on your own infrastructure. One script tag to collect, one workspace to route, and a provisioned ClickHouse on the other side. Or send everything to Snowflake, BigQuery, Redshift, Postgres, MySQL. Capturing events is unlimited and free. We only charge for events we deliver to a destination. Need to change an event on its way through? Write a function in the workspace and we run it on everything in flight. MIT licensed, so the whole thing is yours to read, change and run. 200k delivered events a month, free.

Introducing Jitsu, the open source event data pipeline. Every signup, click and payment in your product is an event. Most companies ship those off to a vendor and pay by the event to read them back. We run the same job on your own infrastructure. One script tag to collect, one workspace to route, and a provisioned ClickHouse on the other side. Or send everything to Snowflake, BigQuery, Redshift, Postgres, MySQL. Capturing events is unlimited and free. We only charge for events we deliver to a destination. Need to change an event on its way through? Write a function in the workspace and we run it on everything in flight. MIT licensed, so the whole thing is yours to read, change and run. 200k delivered events a month, free.

Soham Mehta

36,630 views • 1 month ago

I believe in showing rather than talking. The first video shows how an attacker could escalate their privileges and perform administrative functions on your API using Xjwt. The second video shows how you can protect App and your company from such embarrassment by scanning your token on the tool to assess its security strength. Share this with your technical team, it’s free and open-source.

I believe in showing rather than talking. The first video shows how an attacker could escalate their privileges and perform administrative functions on your API using Xjwt. The second video shows how you can protect App and your company from such embarrassment by scanning your token on the tool to assess its security strength. Share this with your technical team, it’s free and open-source.

Ghost St Badmus

42,827 views • 10 months ago

introducing operator-1, an autonomous document extraction agent operator-1 saturates multiple 3rd party benchmarks, and delivers the most accurate performance on complex tasks that other solutions can't handle: > long tables with thousands of rows > lengthy files with context scattered across hundreds of pages > dense diagrams and images > much more! operator-1 is a specialized agent we built that: - runs within a custom workspace - knows how to use dedicated tools (parse, search, zoom, code execution, validation) to handle any document - learns via persistent memory

introducing operator-1, an autonomous document extraction agent operator-1 saturates multiple 3rd party benchmarks, and delivers the most accurate performance on complex tasks that other solutions can't handle: > long tables with thousands of rows > lengthy files with context scattered across hundreds of pages > dense diagrams and images > much more! operator-1 is a specialized agent we built that: - runs within a custom workspace - knows how to use dedicated tools (parse, search, zoom, code execution, validation) to handle any document - learns via persistent memory

Kushal Byatnal

20,838 views • 15 hours ago

If the engine is strong enough, you should be able to build real products on top of it. That's the whole point of LTX-2.3. Introducing LTX Desktop. A fully local, open-source video editor running directly on the LTX engine, optimized for NVIDIA GPUs and compatible hardware.

If the engine is strong enough, you should be able to build real products on top of it. That's the whole point of LTX-2.3. Introducing LTX Desktop. A fully local, open-source video editor running directly on the LTX engine, optimized for NVIDIA GPUs and compatible hardware.

LTX

954,723 views • 7 months ago

Introducing Candy Machine 🍭🤖 An AI-powered vault that doesn't open with keys, it opens with prompts. To open it? You’ve got to prompt your way in. Craft the right prompt, convince the AI, and the reward is yours. Built on Aptos by Cluster Protocol Think you can outsmart AI ->

Introducing Candy Machine 🍭🤖 An AI-powered vault that doesn't open with keys, it opens with prompts. To open it? You’ve got to prompt your way in. Craft the right prompt, convince the AI, and the reward is yours. Built on Aptos by Cluster Protocol Think you can outsmart AI ->

Cluster Protocol

100,611 views • 1 year ago