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 Monid, the OpenRouter for agent tools. Your agent shouldn't need another subscription just to make three API calls. We connect your agent to 1,700 APIs. It only pays for the calls it makes. > SEO, leads, ecom, stocks, search, video/image/music/3D gen, private company data > discover, inspect, and... show more

Jasper Li

2,541 subscribers

146,360 views • 1 month ago •via X (Twitter)

Science & Technology Finance

Anya Rossi• Live Now

Private livecam show

41 Comments

Jasper Li1 month ago

Try it now:

Vadim1 month ago

the monid team is on a roll 🔥

Jasper Li1 month ago

Love to hear it❤️

Ted | unfair.so1 month ago

leeets go, great work team!

baba yaga1 month ago

Let's go 🔥

Virgile RIETSCH1 month ago

wow this is amazing man!! Just used this with Hermes, it’s crazy good.

leo1 month ago

keeping the monid team on my radar. this is sick

Aman1 month ago

this is exactly the kind of infra agents need no more random subscriptions for every tool

Jasper Li1 month ago

We integrate 1700+tools into one. Come to try.

Daniel Smidstrup1 month ago

Could definitely be quite nice! Having so many subs just adds even more confusion when things change so fast.

Jasper Li1 month ago

Yeah, all ur agent needs in monid

Jeroen van Welsenes1 month ago

This looks so promising!

Harshil Tomar1 month ago

less go !

Hriday Kadam1 month ago

lfgggg killed it !!!

TadasG 💻1 month ago

insane! You guys should integrate MCP ;)

Jasper Li1 month ago

looks interesting

Khushi1 month ago

Team on fire 🔥

Shengkun Ye1 month ago

🔥🔥🔥

Julien Talbot1 month ago

Hermes Agent by @NousResearch + Composio by @composio + Monid by @MonidHQ = 🔥

Vladyslav Pliner1 month ago

🚀

Abdul1 month ago

did u guys just kill per-tool subscriptions for ai agents?

Stephen unfair.so1 month ago

these guys are unstoppable!!

unfair.so1 month ago

congrats team! keep cooking!

Bhavya1 month ago

Did you guys just kill subscriptions!????

Oliver1 month ago

Looks very interesting

arc.1 month ago

will definitely try this

Yush Stha1 month ago

the idea is really great, can I try some?

Mohit Vaswani1 month ago

lfgggg very useful product !!!

Jasper Li1 month ago

🫡🫡

Atta 🐬1 month ago

pay per call instead of another subscription is the whole unlock. nobody wants a SaaS seat so their agent can make three requests.

Jasper Li1 month ago

We killed subscriptions

Atta 🐬1 month ago

this is exactly what we need 🔥

Maya1 month ago

🔥🔥🔥

Deni1 month ago

“Openrouter for agent tools” after stripe acquired them is a big brain marketing move lol

Sentienter AI1 month ago

Wait...what? This is incredible!😍

Cory McAboy1 month ago

I guess engineers are turning into marketers.

Rivaldo A.1 month ago

how are you handling latency overhead when routing through 1,700 endpoints? we noticed a huge spike in agent drop-offs past 400ms.

Rohit1 month ago

1,700+ APIs in one place is huge. The pay-per-call model is even better, agents only pay for what they actually use. This could make building AI agents much simpler.

Hakimuddin K1 month ago

This looks amazing buddy. Hope to use it soon.

Oban1 month ago

Woah! This is impressive

Anissa1 month ago

Pay per use sounds like the future.

Related Videos

We just killed…everything. Introducing Monid, the OpenRouter for agent tools. Today we crossed 4M agent transactions. And raised a $2.1M pre-seed to kill every subscription in the world. Your agents can now: > discover, run, and pay for tools at runtime > one connection to 1,800 APIs: SEO, leads, search, ecommerce, stocks, video/image/music/3D gen, private company data > all pay per call, 0 subscriptions

We just killed…everything. Introducing Monid, the OpenRouter for agent tools. Today we crossed 4M agent transactions. And raised a $2.1M pre-seed to kill every subscription in the world. Your agents can now: > discover, run, and pay for tools at runtime > one connection to 1,800 APIs: SEO, leads, search, ecommerce, stocks, video/image/music/3D gen, private company data > all pay per call, 0 subscriptions

Shengkun Ye

657,271 views • 1 month ago

We just raised $7.7M to kill every subscription for agents. Introducing the openrouter for agent tools. Your agents can now: > discover, run, and pay for tools at runtime > use 2,500 APIs through one connection: leads, SEO, marketing, search, ecommerce, stocks, video/image/music/3D gen, agent email & phone > pay per call, 0 subscriptions

We just raised $7.7M to kill every subscription for agents. Introducing the openrouter for agent tools. Your agents can now: > discover, run, and pay for tools at runtime > use 2,500 APIs through one connection: leads, SEO, marketing, search, ecommerce, stocks, video/image/music/3D gen, agent email & phone > pay per call, 0 subscriptions

Shengkun Ye

742,651 views • 6 days ago

Introducing Monid, the easiest way to connect your agent to 1,200+ tools & APIs. Your agent discovers, runs, and pays for tools at runtime. So you'll never sign up for a dozen accounts or pay for subscriptions you barely use. We routed 1M+ tool calls last month. Here's how Monid works.

Introducing Monid, the easiest way to connect your agent to 1,200+ tools & APIs. Your agent discovers, runs, and pays for tools at runtime. So you'll never sign up for a dozen accounts or pay for subscriptions you barely use. We routed 1M+ tool calls last month. Here's how Monid works.

Shengkun Ye

256,598 views • 2 months ago

We just killed PitchBook, Apollo, Semrush, Apify, and Higgsfield. Introducing Monid. We connect your agent to 1,600+ tools and APIs, without any subscriptions. Entire stack: $20,000+/year. Monid: from <$0.01 per request, pay as you go.

We just killed PitchBook, Apollo, Semrush, Apify, and Higgsfield. Introducing Monid. We connect your agent to 1,600+ tools and APIs, without any subscriptions. Entire stack: $20,000+/year. Monid: from <$0.01 per request, pay as you go.

Shengkun

397,796 views • 2 months ago

Introducing OpenRouter for tools ⚒️ Old world: SaaS bundles priced for humans. $139/mo, and you don't even know what's in the box. New world: agents don't care about vendors. They want the best API for the task - and to pay for the result. - 2,600 agent-friendly tools: seo/geo, social, leads, ads... - search by task: see price/request/response, call it - pay per call, no subscriptions - 0% markup - Open-source Try it here:

Introducing OpenRouter for tools ⚒️ Old world: SaaS bundles priced for humans. $139/mo, and you don't even know what's in the box. New world: agents don't care about vendors. They want the best API for the task - and to pay for the result. - 2,600 agent-friendly tools: seo/geo, social, leads, ads... - search by task: see price/request/response, call it - pay per call, no subscriptions - 0% markup - Open-source Try it here:

Jason Zhou

621,641 views • 2 months ago

We just killed Exa, Tavily, SerpAPI, and Brave. Your agent can now search & fetch any webpage for 100% FREE. Them: $7 per 1,000 searches. Us: $0. No subscriptions, no quotas. Humans search Google for free. Agents shouldn't have to pay either. Made possible by TinyFish and Monid.

We just killed Exa, Tavily, SerpAPI, and Brave. Your agent can now search & fetch any webpage for 100% FREE. Them: $7 per 1,000 searches. Us: $0. No subscriptions, no quotas. Humans search Google for free. Agents shouldn't have to pay either. Made possible by TinyFish and Monid.

Shengkun Ye

886,710 views • 1 month ago

Monad is joining us on our mission to kill subscriptions. Your agent can now call Apollo, ElevenLabs, and MiniMax—no account, no API key—and pay per call in USDC on the Monad network. No credits to buy upfront. No subscriptions to manage. Nothing expires. Your agent isn’t a seat. It shouldn’t have to sign up for one. Made possible by Monad and Monid

Monad is joining us on our mission to kill subscriptions. Your agent can now call Apollo, ElevenLabs, and MiniMax—no account, no API key—and pay per call in USDC on the Monad network. No credits to buy upfront. No subscriptions to manage. Nothing expires. Your agent isn’t a seat. It shouldn’t have to sign up for one. Made possible by Monad and Monid

Shengkun Ye

15,353 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

86,438 views • 5 months ago

Introducing Claude for waterfall enrichment. Your agent can now run a waterfall across Apollo, Hunter, Clay, People Data Labs, ContactOut, and Ploid (YC F26) through one connection. The stack: $7,500 a year in subscriptions. Monid: from $0.005 per call. Pay as you go.

Introducing Claude for waterfall enrichment. Your agent can now run a waterfall across Apollo, Hunter, Clay, People Data Labs, ContactOut, and Ploid (YC F26) through one connection. The stack: $7,500 a year in subscriptions. Monid: from $0.005 per call. Pay as you go.

Shengkun Ye

179,007 views • 1 month ago

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →

chetan conikee

469,414 views • 4 months ago

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 own APIs, same key. Change the grant when the job changes. The agent never sees your real credentials. Beta customers already run over 95,000 calls each through it. Watch it work ↓

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 own APIs, same key. Change the grant when the job changes. The agent never sees your real credentials. Beta customers already run over 95,000 calls each through it. Watch it work ↓

mem0

34,282 views • 27 days ago

HERMES AGENT WITHOUT TOOLS IS A CHATBOT. WITH THEM IT BUILDS 3D TOWERS IN BLENDER, CHECKS STOCK PRICES, AND DRIVES VS CODE. tonbi JUST DROPPED THE FULL GUIDE. module 6 of his 10-part Hermes masterclass. best breakdown of the tool layer anyone has published. what you need to know: TOOLS vs SKILLS vs MCP skills = instructions (markdown, loaded into context) tools = callable functions (Python, agent emits call, Hermes executes) MCP = adapters to external systems (Blender, Stripe, Linear, Notion) every tool has three parts: → the function (does the real work) → the schema (what the model sees to decide when to call it) → the registry (makes the tool exist in the agent) the model never runs the function directly. it emits a structured request (tool name + JSON args). Hermes executes and returns the result. if the tool fails, the error goes back as JSON. the agent recovers instead of crashing. TOOL SETS CONTROL THE SURFACE hermes chat --tool-sets web # only web tools loaded. no files, no terminal. hermes chat --tool-sets safe # read-only: web search, vision, image gen. # no file writes. no terminal. no code execution. mid-session: /tools enable video /tools disable terminal or toggle in the dashboard: hermes dashboard → Skills → Tool Sets MCP SERVERS two transport types: STDIO (local subprocess) or HTTP (remote endpoint). add a server: hermes mcp # or ask: "add the MCP server for Blender" filter tools with include/exclude per server. keep only what you trust. security: → OAuth 2.1 PKCE (no long-lived tokens in config) → package scanning via api.osv. dev before launch → all MCP calls go through approval gates HERMES AS MCP SERVER hermes mcp serve exposes 10 tools via FastMCP. connect VS Code Copilot or Cursor to your running Hermes instance. BUILD YOUR OWN TOOL He built a stock price tool live: → Python function calling Finnhub API → schema with name, description, parameters → registered in tool_sets.py → agent calls it automatically when relevant any repeating API call in your workflow can become a native tool. full Hermes architecture deep-dive in the article 👇

HERMES AGENT WITHOUT TOOLS IS A CHATBOT. WITH THEM IT BUILDS 3D TOWERS IN BLENDER, CHECKS STOCK PRICES, AND DRIVES VS CODE. tonbi JUST DROPPED THE FULL GUIDE. module 6 of his 10-part Hermes masterclass. best breakdown of the tool layer anyone has published. what you need to know: TOOLS vs SKILLS vs MCP skills = instructions (markdown, loaded into context) tools = callable functions (Python, agent emits call, Hermes executes) MCP = adapters to external systems (Blender, Stripe, Linear, Notion) every tool has three parts: → the function (does the real work) → the schema (what the model sees to decide when to call it) → the registry (makes the tool exist in the agent) the model never runs the function directly. it emits a structured request (tool name + JSON args). Hermes executes and returns the result. if the tool fails, the error goes back as JSON. the agent recovers instead of crashing. TOOL SETS CONTROL THE SURFACE hermes chat --tool-sets web # only web tools loaded. no files, no terminal. hermes chat --tool-sets safe # read-only: web search, vision, image gen. # no file writes. no terminal. no code execution. mid-session: /tools enable video /tools disable terminal or toggle in the dashboard: hermes dashboard → Skills → Tool Sets MCP SERVERS two transport types: STDIO (local subprocess) or HTTP (remote endpoint). add a server: hermes mcp # or ask: "add the MCP server for Blender" filter tools with include/exclude per server. keep only what you trust. security: → OAuth 2.1 PKCE (no long-lived tokens in config) → package scanning via api.osv. dev before launch → all MCP calls go through approval gates HERMES AS MCP SERVER hermes mcp serve exposes 10 tools via FastMCP. connect VS Code Copilot or Cursor to your running Hermes instance. BUILD YOUR OWN TOOL He built a stock price tool live: → Python function calling Finnhub API → schema with name, description, parameters → registered in tool_sets.py → agent calls it automatically when relevant any repeating API call in your workflow can become a native tool. full Hermes architecture deep-dive in the article 👇

YanXbt

32,680 views • 4 months ago

We just shipped self-serve for Locus Pro, the first OpenRouter for everything. You shouldn’t need a dozen subscriptions just to make your agent useful. Get access to 3,300+ providers and 16,000+ agent tools all through one prepaid balance. Sign up, paste in the MCP URL, turn on the tools you want. Your agent can use OpenAI, Anthropic, Firecrawl, ElevenLabs, Exa and thousands more without you opening a single new account. No subscriptions or monthly minimum, top up with as little as $5.

We just shipped self-serve for Locus Pro, the first OpenRouter for everything. You shouldn’t need a dozen subscriptions just to make your agent useful. Get access to 3,300+ providers and 16,000+ agent tools all through one prepaid balance. Sign up, paste in the MCP URL, turn on the tools you want. Your agent can use OpenAI, Anthropic, Firecrawl, ElevenLabs, Exa and thousands more without you opening a single new account. No subscriptions or monthly minimum, top up with as little as $5.

cole

57,228 views • 1 month ago

I made a video breaking down AI agent observability and evals, and ran the whole thing on open source. If you build agents, sooner or later you watch one run and realise you have no idea what it just did, or what it cost you. That gap is what observability and evals are for. Least glamorous part of the stack, and the part you end up needing most. 🛠️ treg, OpenRouter for agent tools (4.2k): 🔑 Try treg: 🌟 Github Repo (2k): 💻 Portable memory: ☕ Join our community: Observability is a camera. It records what ran, how long, what it cost. Eval is a referee. It decides whether the run was good enough to ship. I ran it on Treg for the tool calls and Waku Agent for the memory. treg is an OpenRouter for agent tool calls, so your agent carries one API key instead of one per tool. Both open source, so you can read the code rather than take my word for it. Full video in the first reply 👇 You Can Build Anything. You Can Learn Anything. 💪

I made a video breaking down AI agent observability and evals, and ran the whole thing on open source. If you build agents, sooner or later you watch one run and realise you have no idea what it just did, or what it cost you. That gap is what observability and evals are for. Least glamorous part of the stack, and the part you end up needing most. 🛠️ treg, OpenRouter for agent tools (4.2k): 🔑 Try treg: 🌟 Github Repo (2k): 💻 Portable memory: ☕ Join our community: Observability is a camera. It records what ran, how long, what it cost. Eval is a referee. It decides whether the run was good enough to ship. I ran it on Treg for the tool calls and Waku Agent for the memory. treg is an OpenRouter for agent tool calls, so your agent carries one API key instead of one per tool. Both open source, so you can read the code rather than take my word for it. Full video in the first reply 👇 You Can Build Anything. You Can Learn Anything. 💪

Shen Sean Chen

31,983 views • 6 days ago

Introducing Enchant One place to use AI tools without building or running your own agent Ask for research, browser work, images, documents, email, and more. Choose a tool, pay a few cents, and get the result One account, no subscriptions - 100+ tools Need something? Just ask Enchant🪄

Introducing Enchant One place to use AI tools without building or running your own agent Ask for research, browser work, images, documents, email, and more. Choose a tool, pay a few cents, and get the result One account, no subscriptions - 100+ tools Need something? Just ask Enchant🪄

Ken Wattana

22,280 views • 2 months ago

We shipped big changes for Cloudflare Developers AI Search! Every agent needs search and it shouldn't take a week to set up. AI Search is the search primitive for your agents. Create an instance, upload your data, and search it. Comes with hybrid retrieval with vector and BM25.

We shipped big changes for Cloudflare Developers AI Search! Every agent needs search and it shouldn't take a week to set up. AI Search is the search primitive for your agents. Create an instance, upload your data, and search it. Comes with hybrid retrieval with vector and BM25.

Anni Wang

12,975 views • 5 months ago

I've been trying a tool called treg. It handles one of the annoying parts of working with agents: finding the right API for a task. You describe the job. treg searches its catalog, shows the available providers and prices, then lets your agent call the selected endpoint with one token. I tested it with a question I would ask in real work: "What AI coding topics are trending on X right now?" The agent searched for an X post API, compared the options, picked one, pulled the posts, and summarized the topics. I like the idea behind it: "Ask for the task, not the tool." treg is OpenRouter for agent tools. - 2,630 endpoints across 47 providers - pay per call at provider rates, no subscription or markup - open source

I've been trying a tool called treg. It handles one of the annoying parts of working with agents: finding the right API for a task. You describe the job. treg searches its catalog, shows the available providers and prices, then lets your agent call the selected endpoint with one token. I tested it with a question I would ask in real work: "What AI coding topics are trending on X right now?" The agent searched for an X post API, compared the options, picked one, pulled the posts, and summarized the topics. I like the idea behind it: "Ask for the task, not the tool." treg is OpenRouter for agent tools. - 2,630 endpoints across 47 providers - pay per call at provider rates, no subscription or markup - open source

Kai

13,316 views • 1 month ago

AgentCRM is the first CRM built for AI agents, not humans. Your agent can synthesize real-time data, curate it, format it into an email, and send it to your list. On its own, every day. What makes it different? 3 API calls to go from zero to sending a newsletter. Create org, add contacts, send. No onboarding wizard, no domain setup, no OAuth. Agent-first SDK. pip install agentcrm Built on AgentMail (YC S25) for delivery. No SMTP config. Connect your AgentMail key and emails go out. Suppression is automatic. Bounces, complaints, and unsubscribes are handled without the agent doing anything. DM me for developer access or questions.

AgentCRM is the first CRM built for AI agents, not humans. Your agent can synthesize real-time data, curate it, format it into an email, and send it to your list. On its own, every day. What makes it different? 3 API calls to go from zero to sending a newsletter. Create org, add contacts, send. No onboarding wizard, no domain setup, no OAuth. Agent-first SDK. pip install agentcrm Built on AgentMail (YC S25) for delivery. No SMTP config. Connect your AgentMail key and emails go out. Suppression is automatic. Bounces, complaints, and unsubscribes are handled without the agent doing anything. DM me for developer access or questions.

Rani Haddad

29,492 views • 6 months 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