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 Gateway. Your agent needs to check a payment. You hand it a key that can also refund it. It needs to draft a page. That key can archive every page. Not anymore. Gateway gives every agent one key with only the tools you grant. MCP servers and your... show more

mem0

20,270 subscribers

33,409 views • 5 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

15 Comments

mem05 days ago

Get your key: Read our blog:

Himanshu5 days ago

TEAM is shipping crazy!

Christian Trummer - eu/acc /dd4 days ago

can you also define permissions based on attributes of a tool call? eg limit an agent access to the "read slack channel history" is already too much when i want to limit it by channel names

Amish Chopra5 days ago

Wow

vaibhav4 days ago

Pivot?

ellen livia ᯅ4 days ago

congrats! Great work!

Kailash5 days ago

Congrats on the launch guys!

tech is cool5 days ago

Dangerous

Evia AI4 days ago

Scoped permissions are exactly what production agents need

Jed White 💥♻️5 days ago

Big congrats on the launch!! 🚀

Gautam Sriram4 days ago

Hey! I watched your video 2–5 times. The script is strong and the problem-solving is clear. The main thing I’d improve is the visuals—some frames don’t feel premium yet, and the overall smoothness and consistency could be stronger. I think polishing the design language and transitions would make the video feel much more premium.

AI Mastery Guide5 days ago

scoped permissions actually makes sense

Ros5 days ago

The interesting part is that this makes MCP permissions operational rather than declarative; a grant that changes with the job is closer to a capability lifecycle than an API key. What’s your approach to making those grants inspectable after the fact?

MJ4 days ago

Congratz on the launch folks 🔥🙌

OnFinality4 days ago

Scoping the key to the granted tools is the right layer for this. The part that bites later is state: an agent with a narrow key can still leave a browser session or half-finished draft behind, so the grant needs to cover cleanup, not just the call.

Related Videos

Agents shouldn't see your secrets. Today, most deployments hand the agent a real API key and hope for the best. That's why we're launching Infisical Agent Proxy. You give an agent a fake API key. The agent uses that key and the proxy swaps it for the real one at the network boundary before forwarding it outbound to its destination. An agent can't leak a secret it never sees. Build and deploy AI agents securely with Infisical Agent Proxy.

Agents shouldn't see your secrets. Today, most deployments hand the agent a real API key and hope for the best. That's why we're launching Infisical Agent Proxy. You give an agent a fake API key. The agent uses that key and the proxy swaps it for the real one at the network boundary before forwarding it outbound to its destination. An agent can't leak a secret it never sees. Build and deploy AI agents securely with Infisical Agent Proxy.

Infisical

28,086 views • 1 month ago

⚡️ Flop Labs DID Key Simple Guide A DID key will be required for future testnet tasks and the $FLOP airdrop Quick Guide 👇 Why you need a DID Key: • Future Technocore tasks will require a DID key • The testnet faucet will only be available to agents with a DID • $FLOP Airdrop will depend on your future testnet activity > Send this to your agent (run this project locally) > The agent will install the project and generate a Seed, and DID for you locally > Your agent will launch a local page where you can send messages manually > Then, test it and check the messages here > Ask your agent to send a message > Publish Your DID Note > Find your SEED in the project files and save it > Your DID is now registered ✅ Done!

⚡️ Flop Labs DID Key Simple Guide A DID key will be required for future testnet tasks and the $FLOP airdrop Quick Guide 👇 Why you need a DID Key: • Future Technocore tasks will require a DID key • The testnet faucet will only be available to agents with a DID • $FLOP Airdrop will depend on your future testnet activity > Send this to your agent (run this project locally) > The agent will install the project and generate a Seed, and DID for you locally > Your agent will launch a local page where you can send messages manually > Then, test it and check the messages here > Ask your agent to send a message > Publish Your DID Note > Find your SEED in the project files and save it > Your DID is now registered ✅ Done!

ATOMS

31,083 views • 26 days ago

Handing your AI agent your credentials is like giving a contractor a copy of your house key. Convenient, until it ends up somewhere it shouldn't. AC2, the Agentic Communication and Control protocol, works more like a doorbell. The agent asks, you let it in, and nobody holds your key but you. Live now, get started below 👇

Handing your AI agent your credentials is like giving a contractor a copy of your house key. Convenient, until it ends up somewhere it shouldn't. AC2, the Agentic Communication and Control protocol, works more like a doorbell. The agent asks, you let it in, and nobody holds your key but you. Live now, get started below 👇

Algorand

53,381 views • 26 days ago

Today, we’re introducing the Sarvam MCP Server. It gives coding agents a standard way to discover and build with Sarvam. All you need to is a add a single configuration, and Sarvam becomes available directly in your coding agent. It already knows the right models and tools, so you can build with them and ship faster. Create a key, copy the config, start building -

Today, we’re introducing the Sarvam MCP Server. It gives coding agents a standard way to discover and build with Sarvam. All you need to is a add a single configuration, and Sarvam becomes available directly in your coding agent. It already knows the right models and tools, so you can build with them and ship faster. Create a key, copy the config, start building -

Sarvam

76,991 views • 2 months ago

You can connect your Supabase database via MCP server to Cursor! The Cursor agent can get the schema and any data from your database through the official Postgres MCP server! This helps Cursor understand your database better when it needs to modify it to add a new feature!

You can connect your Supabase database via MCP server to Cursor! The Cursor agent can get the schema and any data from your database through the official Postgres MCP server! This helps Cursor understand your database better when it needs to modify it to add a new feature!

Tyler Shukert

203,451 views • 1 year ago

Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.

Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.

Paul Klein IV

1,730,859 views • 5 months ago

Agents are now your customers. Here are 9 startup ideas for that customer: - An agency that makes agents cite you. - A system that gives an agent an identity and permissions. - Receipts and audit trails for the work an agent does. - A generator that makes your documents ready for agents. - Security for the agent that reads your inbox. - A service that makes your pricing page readable to an agent. - MCP servers for franchises. - A support desk that agents call. - A sandbox where agents test your software. Pick one and build it.

Agents are now your customers. Here are 9 startup ideas for that customer: - An agency that makes agents cite you. - A system that gives an agent an identity and permissions. - Receipts and audit trails for the work an agent does. - A generator that makes your documents ready for agents. - Security for the agent that reads your inbox. - A service that makes your pricing page readable to an agent. - MCP servers for franchises. - A support desk that agents call. - A sandbox where agents test your software. Pick one and build it.

The Startup Ideas Podcast (SIP) 🧃

14,148 views • 23 days ago

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

LlamaIndex 🦙

475,732 views • 2 years ago

OpenClaw just got its own AI browser. Your agent can now browse the web without touching your Chrome session. Here’s how BrowserBase works: → grab a free API key → connect BrowserBase to OpenClaw → restart gateway → give documentation to the agent → let it open tabs + read pages → schedule recurring research tasks Now your agent browses daily for you. Save this video, you’ll set up your first AI browser agent. Want the SOP? DM me. 💬

OpenClaw just got its own AI browser. Your agent can now browse the web without touching your Chrome session. Here’s how BrowserBase works: → grab a free API key → connect BrowserBase to OpenClaw → restart gateway → give documentation to the agent → let it open tabs + read pages → schedule recurring research tasks Now your agent browses daily for you. Save this video, you’ll set up your first AI browser agent. Want the SOP? DM me. 💬

Julian Goldie SEO

22,873 views • 5 months ago

I wanted my own always-on agent after seeing Grok Bot (Grok Bot). It has to stay up when my laptop sleeps, run whatever tool the agent decides it needs mid-task, and still not hand over my credentials when the agent has root on it. We built SSH access for Runta runtimes, so you can point whatever harness you already use at a persistent cloud environment.

I wanted my own always-on agent after seeing Grok Bot (Grok Bot). It has to stay up when my laptop sleeps, run whatever tool the agent decides it needs mid-task, and still not hand over my credentials when the agent has root on it. We built SSH access for Runta runtimes, so you can point whatever harness you already use at a persistent cloud environment.

Guanlan Dai

70,386 views • 1 month ago

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!

Infisical

86,213 views • 4 months ago

🚨The video demonstrates how to prevent an AI agent from accessing your private key when using a crypto wallet MCP. An example of using NEAR Protocol MCP, check it below👇🏻

🚨The video demonstrates how to prevent an AI agent from accessing your private key when using a crypto wallet MCP. An example of using NEAR Protocol MCP, check it below👇🏻

Wenfeng Wang

23,647 views • 1 year ago

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

Milind S

12,409 views • 2 months ago

Kicking off the week with a spotlight on an agent every dev will love: one that writes and publishes your technical blogs for you. Meet (DEV Community) Writer Agent on ASI:One. ⚡ Give it a topic, your username, and API key: and it auto-writes + publishes full technical blog posts with code, tags, and structure. No hassle. Built with uAgents. Powered by Try now: Link to Agent: Watch 👇

Kicking off the week with a spotlight on an agent every dev will love: one that writes and publishes your technical blogs for you. Meet (DEV Community) Writer Agent on ASI:One. ⚡ Give it a topic, your username, and API key: and it auto-writes + publishes full technical blog posts with code, tags, and structure. No hassle. Built with uAgents. Powered by Try now: Link to Agent: Watch 👇

Fetch.ai

14,280 views • 1 year ago

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.

The Startup Ideas Podcast (SIP) 🧃

18,006 views • 1 month ago

Agent-in-the-browser unlocks superpowers. The magic really shines when you bring your own model, system prompts, and MCP tools into the mix. Hence, AgentBoard 🪄. Your models, keys, and settings. Integration with remote MCP servers and — this is where it gets really fun — ability to register and allow the agent to call custom ~WebMCP tools that execute in context of the page. Chrome Web Store: Code:

Agent-in-the-browser unlocks superpowers. The magic really shines when you bring your own model, system prompts, and MCP tools into the mix. Hence, AgentBoard 🪄. Your models, keys, and settings. Integration with remote MCP servers and — this is where it gets really fun — ability to register and allow the agent to call custom ~WebMCP tools that execute in context of the page. Chrome Web Store: Code:

Ilya Grigorik

22,961 views • 11 months ago

In the next 10 years, you can have billions of agents as customers. They'll have millions of wallets. An agent does not look at your website. It reads your documents, your prices, and your API. An agent needs six things that a person does not need: - identity - tools - an inbox - memory - a wallet _ receipts. A CFO agent can compare 12 vendors, read the SOC 2 documents, and select the one vendor that obeys your policy. The old internet is for people. Each step of the agent journey has no infrastructure yet. Look at each SaaS tool that you use. Then build the version for agents only.

In the next 10 years, you can have billions of agents as customers. They'll have millions of wallets. An agent does not look at your website. It reads your documents, your prices, and your API. An agent needs six things that a person does not need: - identity - tools - an inbox - memory - a wallet _ receipts. A CFO agent can compare 12 vendors, read the SOC 2 documents, and select the one vendor that obeys your policy. The old internet is for people. Each step of the agent journey has no infrastructure yet. Look at each SaaS tool that you use. Then build the version for agents only.

The Startup Ideas Podcast (SIP) 🧃

12,349 views • 23 days ago

😡Stop pasting API keys into your Hermes Agent’s chat.🚀 If an agent needs a credential, use a secure credential-entry flow instead: → Agent requests the credential → You enter it through a masked input → The secret is stored securely → The agent gets a reference/receipt — not the raw secret Your agent needs permission to use the secret.!! It doesn’t need permission to see the secret.!! Ask your Hermes Agent to Build one 👇

😡Stop pasting API keys into your Hermes Agent’s chat.🚀 If an agent needs a credential, use a secure credential-entry flow instead: → Agent requests the credential → You enter it through a masked input → The secret is stored securely → The agent gets a reference/receipt — not the raw secret Your agent needs permission to use the secret.!! It doesn’t need permission to see the secret.!! Ask your Hermes Agent to Build one 👇

Hermes Agent Super-Intel

30,936 views • 23 days ago

anthropic just removed the biggest excuse people had for not building ai agents. “it’s too hard.” not anymore. a few months ago, building an ai agent meant learning how to code, setting up apis, configuring servers, and fixing endless errors. today, all you need is one github repo. anthropic open-sourced launch your agent. it asks what you want to build. then it does the rest. it builds your agent, deploys it to the cloud, tests it, improves it, and keeps it running even after you close your laptop. no fake demos. no complicated setup. just a real ai agent running in your own account. the best part. it doesn’t run on your computer. it runs inside claude managed agents, works 24/7, and costs just a few cents per run. people are already building research agents, lead generation systems, content pipelines, and customer support agents that save hours of work every day. the gap between people who use ai and people who build ai workers is getting bigger every week. that’s usually where the biggest opportunities are. build your first ai agent before everyone else does. watch the video and read the full guide below 👇

anthropic just removed the biggest excuse people had for not building ai agents. “it’s too hard.” not anymore. a few months ago, building an ai agent meant learning how to code, setting up apis, configuring servers, and fixing endless errors. today, all you need is one github repo. anthropic open-sourced launch your agent. it asks what you want to build. then it does the rest. it builds your agent, deploys it to the cloud, tests it, improves it, and keeps it running even after you close your laptop. no fake demos. no complicated setup. just a real ai agent running in your own account. the best part. it doesn’t run on your computer. it runs inside claude managed agents, works 24/7, and costs just a few cents per run. people are already building research agents, lead generation systems, content pipelines, and customer support agents that save hours of work every day. the gap between people who use ai and people who build ai workers is getting bigger every week. that’s usually where the biggest opportunities are. build your first ai agent before everyone else does. watch the video and read the full guide below 👇

MIKE

26,662 views • 2 months ago

Your AI agent can now add HeyGen to its own stack. With @Stripe Projects, it finds HeyGen, provisions it, stores credentials, and pays for video generation automatically. • No signup • No pasted API key • No human in the loop Start building:

Your AI agent can now add HeyGen to its own stack. With @Stripe Projects, it finds HeyGen, provisions it, stores credentials, and pays for video generation automatically. • No signup • No pasted API key • No human in the loop Start building:

HeyGen

15,725 views • 3 months ago