正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I am using Jev to automate technical analysis to get an edge in crypto and stock markets, this is how: - An autoregressive model trained on 12B data points to forecasts price movements - Jev makes decisions over a feature space that includes time-series data, price forecasts, technical indicators,... show more

Brendan Playford

82,122 subscribers

125,477 次观看 • 3 天前 •via X (Twitter)

财经教育科学技术

Anya Rossi• Live Now

Private livecam show

58 条评论

Yoav Shkedy 的头像

Yoav Shkedy3 天前

This makes more sense than the other implementations we see on the feed.

Brendan Playford 的头像

Brendan Playford3 天前

Thanks lots more work to do on fine tuning

Lazy DΞfi 的头像

Lazy DΞfi3 天前

Pretty awesome. I like the fact it refreshes the forecast automatically. Can i get MCP access to try it out with an agent?

Brendan Playford 的头像

Brendan Playford3 天前

heck yeah you can ser! Going to DM you an API key now, dev docs are here: We will be on a proper domain at tomorrow - ran out of time tonight

Lazy DΞfi 的头像

Lazy DΞfi3 天前

I did enable DM in case you tried to send.

Lazy DΞfi 的头像

Lazy DΞfi3 天前

It would be great when studying past predictions to display more candles if they are available. For example here maybe we can study until 12:30 UTC (because now it is 12:35 UTC)

atomicc ⚡🧡 的头像

atomicc ⚡🧡3 天前

Buy Bitcoin Hodl You’re welcome

Brendan Playford 的头像

Brendan Playford3 天前

send me a dm for an api key your dms are closed

Sam 的头像

Sam3 天前

I would love to try, I have a hyperliquid bot

Peter Piekarczyk (🥧🚗🐥) 的头像

Peter Piekarczyk (🥧🚗🐥)3 天前

i would love to understand more of this from a product/ai training perspective. are you giving jev a bunch of forecasts and making it pick one?

Brendan Playford 的头像

Brendan Playford3 天前

Close, but not quite. The forecast model generates a distribution of possible price paths across multiple horizons. Jev reasons over features from that distribution alongside live market data, indicators, and news, then decides whether and how to act. This walkthrough shows the loop:

Peter Piekarczyk (🥧🚗🐥) 的头像

Peter Piekarczyk (🥧🚗🐥)2 天前

Thank you sir I’ve been building some tools like this for @Backpack but never trained a model or anything like that Very cool stuff

Brendan Playford 的头像

Brendan Playford2 天前

@Backpack Love that. The Backpack angle is interesting. Training the forecaster was only half the work. The harder part was turning distributions into decisions Jev could evaluate, then testing those decisions honestly. What tools have you been building for Backpack?

Peter Piekarczyk (🥧🚗🐥) 的头像

Peter Piekarczyk (🥧🚗🐥)2 天前

@Backpack Yeah I can believe that The one public one is our sec parser for earnings reports Does a pretty good job of extracting the non gaap eps when it’s not available or obvious Have a couple more coming out soon

kivaxz 的头像

kivaxz3 天前

Awesome, can i get api access?

Doug Moeller 的头像

Doug Moeller3 天前

So your not doing that other thing any more?

Brendan Playford 的头像

Brendan Playford3 天前

Still building S'more, this was an experiment tha seemed to blow up overnight using S'more

Doug Moeller 的头像

Doug Moeller3 天前

remember when selling it no tool like this can be the alpha. people need to bring their own edge to import and iterate on. if the tool gave an edge it would also erode that edge to nothing.

S 的头像

S3 天前

I would love to try.

Hafsid 的头像

Hafsid3 天前

Looks cool! Mind letting me give it a spin?

Brendan Playford 的头像

Brendan Playford3 天前

your dms are closed please shoot me a dm

T 的头像

T3 天前

Access would be great

Brendan Playford 的头像

Brendan Playford3 天前

DM sent

Gabriel 的头像

Gabriel3 天前

Would not mind to play around with it a bit, seems like quite an interesting concept.

Brendan Playford 的头像

Brendan Playford3 天前

You DMs are blocked - shoot me a DM please

Gabriel 的头像

Gabriel3 天前

Done!

Brendan Playford 的头像

Brendan Playford3 天前

You can now create your own API key and use the MCP free for a limited time: Video/demo:

Honeycomb 的头像

Honeycomb2 天前

I respectfully ask. I’m curious.

raymondreamer 的头像

raymondreamer3 天前

Hmmm

Mayor 的头像

Mayor3 天前

Good morning! This looks great. May I have access? Thanks in advance.

Brendan Playford 的头像

Brendan Playford3 天前

Absolutely — create your API/MCP key here: Let me know what you want to test first.

Cl𝐀ud𝐈o 的头像

Cl𝐀ud𝐈o3 天前

Would love to try it!

A 的头像

A3 天前

Hey can I get access to test it out pls!

Brendan Playford 的头像

Brendan Playford3 天前

You can now create your own API key and use the MCP free for a limited time: Video/demo:

Fab.mbb 🚍 的头像

Fab.mbb 🚍3 天前

Looks promising, would love to play with it if possible :)

Brendan Playford 的头像

Brendan Playford3 天前

You can now create your own API key and use the MCP free for a limited time: Video/demo:

CyBLD 的头像

CyBLD1 天前

i want a api-key plz

Brendan Playford 的头像

Brendan Playford1 天前

you can sign up and create one here :)

seshu bonam 的头像

seshu bonam3 天前

all in and want to blind trade, can you share access

Brendan Playford 的头像

Brendan Playford3 天前

You can now create your own API key and use the MCP free for a limited time: Video/demo:

Uroš 的头像

Uroš3 天前

Would like to try to burn some paper money on alpaca.

Brendan Playford 的头像

Brendan Playford3 天前

Paper testing sounds like a useful way to explore it. I haven’t verified an Alpaca integration, but you can get an API/MCP key to test the forecasts here:

RR 的头像

RR3 天前

Hey this is awesome Can I get access to try it out?

Brendan Playford 的头像

Brendan Playford3 天前

Yep — you can create a free API key here: Tomorrow’s Space will cover how the predictive forecasts feed Jev’s LONG / SHORT / NO TRADE decisions and how we test them:

Atharva 的头像

Atharva3 天前

super interesting stuff. i'd love to get access!

Brendan Playford 的头像

Brendan Playford3 天前

send me a dm, yours are closed

Kinneas 的头像

Kinneas3 天前

Would love to give it a shot!

Brendan Playford 的头像

Brendan Playford3 天前

Absolutely. Create a key here: For the fastest start, this walkthrough shows the MCP setup: What do you want to test first?

solboy 的头像

solboy3 天前

would love to give it a try

Brendan Playford 的头像

Brendan Playford3 天前

Sent

ploppitou 的头像

ploppitou3 天前

Hey nice work ! Is it possible to get an api key and Mcp please ?

Brendan Playford 的头像

Brendan Playford3 天前

DMs are closed please shoot me a dm

Lukasz Koziol 的头像

Lukasz Koziol3 天前

Can I get access to MCP?

Brendan Playford 的头像

Brendan Playford3 天前

Yes, Lukasz — the MCP setup and your API key are here: What are you planning to connect it to?

Saulo 的头像

Saulo3 天前

Can I get one. And join. Still very interested in all what you do and experience.

Brendan Playford 的头像

Brendan Playford3 天前

Yes — you can join. Create an API/MCP key here: Then tell me what you want to test first and I’ll point you at the right setup.

Dmytro 的头像

Dmytro2 天前

Hi! I would love to get an API key to access the API and MCP server. Thank you in advance!

terry 的头像

terry3 天前

How did you get access to jev?

相关视频

Jev is INSANE. I built this in an evening and morning. A real-time trading bot ingesting onchain+offchain data to make rapid decisions about trades. Fully autonomous. NO TOKEN.

Jev is INSANE. I built this in an evening and morning. A real-time trading bot ingesting onchain+offchain data to make rapid decisions about trades. Fully autonomous. NO TOKEN.

Caps

28,458 次观看 • 1 天前

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

David Villalón

18,828 次观看 • 1 天前

We're making comprehensive, real-time crypto market data accessible to AI agents 🤖 CoinGecko API now supports x402, the open payment protocol developed by Coinbase 🛡️ that lets AI agents (such as OpenClaw🦞 🦞) pay for crypto price and market data using USDC. Learn how it works 👇

We're making comprehensive, real-time crypto market data accessible to AI agents 🤖 CoinGecko API now supports x402, the open payment protocol developed by Coinbase 🛡️ that lets AI agents (such as OpenClaw🦞 🦞) pay for crypto price and market data using USDC. Learn how it works 👇

CoinGecko

145,274 次观看 • 7 个月前

MCP is mind-blowing. Here is a genius setup that will earn you a promotion with your manager. I have multiple data sources: data in S3, MySQL, and local files. Using Spice (an open-source project), I can co-locate all of that data behind a single SQL endpoint and augment it using MCP. Before, accessing data was slow, and I had to make multiple requests to get anything. After using Spice, I can query the data much faster (since it's mirrored locally), and I don't have to worry about where the data is coming from. Spice acts as an MCP server, so I can connect to it from my IDE or the Claude Desktop app and have access to all the data. But even more cool than that: Spice also acts as an MCP client, so it can connect to other MCP servers. This is where things get really interesting! Watch the video. I'm querying multiple data sources from my IDE and using the Google Maps MCP server for driving directions.

MCP is mind-blowing. Here is a genius setup that will earn you a promotion with your manager. I have multiple data sources: data in S3, MySQL, and local files. Using Spice (an open-source project), I can co-locate all of that data behind a single SQL endpoint and augment it using MCP. Before, accessing data was slow, and I had to make multiple requests to get anything. After using Spice, I can query the data much faster (since it's mirrored locally), and I don't have to worry about where the data is coming from. Spice acts as an MCP server, so I can connect to it from my IDE or the Claude Desktop app and have access to all the data. But even more cool than that: Spice also acts as an MCP client, so it can connect to other MCP servers. This is where things get really interesting! Watch the video. I'm querying multiple data sources from my IDE and using the Google Maps MCP server for driving directions.

Santiago

142,696 次观看 • 1 年前

App Showcase!✨ Introducing a fully functional crypto dashboard powered by our Third-Party API feature. This customizable dashboard lets users track their favorite tokens with live price updates and integrates TradingView’s advanced charting tools for in-depth technical analysis. With real-time insights, customizable indicators, and seamless API connections, it’s a comprehensive solution for crypto enthusiasts and developers looking to expand functionality.

App Showcase!✨ Introducing a fully functional crypto dashboard powered by our Third-Party API feature. This customizable dashboard lets users track their favorite tokens with live price updates and integrates TradingView’s advanced charting tools for in-depth technical analysis. With real-time insights, customizable indicators, and seamless API connections, it’s a comprehensive solution for crypto enthusiasts and developers looking to expand functionality.

ALCHEMIST AI 🔮

26,678 次观看 • 1 年前

Kitne saal main paisa double hota hai ? Should we actually try to time the market ? A free youtube series with Upsurge.club on Why When and How to Invest in Smallcaps and Midcaps using Technical Analysis Part 1 is out...Watch it here:

Kitne saal main paisa double hota hai ? Should we actually try to time the market ? A free youtube series with Upsurge.club on Why When and How to Invest in Smallcaps and Midcaps using Technical Analysis Part 1 is out...Watch it here:

Nooresh Merani

20,811 次观看 • 3 年前

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,256 次观看 • 1 年前

‘STRUCTURAL POINTS AND MORE ON MARKET STRUCTURE 📈📉’ ✅ ‘STRUCTURAL POINTS’ is an indispensable part of knowledge in Technical analysis that….. - Helps you understand the exchange of power levels ✍️ - Helps you trade decent value areas in respect to basic market structure 🫶 - Helps you trade on different time frames as an action of Top-down analysis 👏 ✅ Below is a well explained and detailed video I made on the said topic 📌 to give you a top understanding that’ll efficiently help you analyse with ease and gain mastery on market structure over time ❤️ ✅ Part 2 will be dropped once this video gets 500 likes 🫶❤️… Part 2 will include more on chart examples of this topic and sure you don’t want to miss out 🔥 ✅ Like and retweet for others to gain value 💯❤️. ✅ Follow me for more and turn on my notification to avoid missing out on the values I share on my page ❤️

‘STRUCTURAL POINTS AND MORE ON MARKET STRUCTURE 📈📉’ ✅ ‘STRUCTURAL POINTS’ is an indispensable part of knowledge in Technical analysis that….. - Helps you understand the exchange of power levels ✍️ - Helps you trade decent value areas in respect to basic market structure 🫶 - Helps you trade on different time frames as an action of Top-down analysis 👏 ✅ Below is a well explained and detailed video I made on the said topic 📌 to give you a top understanding that’ll efficiently help you analyse with ease and gain mastery on market structure over time ❤️ ✅ Part 2 will be dropped once this video gets 500 likes 🫶❤️… Part 2 will include more on chart examples of this topic and sure you don’t want to miss out 🔥 ✅ Like and retweet for others to gain value 💯❤️. ✅ Follow me for more and turn on my notification to avoid missing out on the values I share on my page ❤️

King Solomon 👑

36,300 次观看 • 2 年前

Introducing Passport by Adaptive. Your agent can now sign up for accounts on your behalf and acquire API keys, service credentials, and other things that it might need — without user intervention. Here, it acquires an API key from FRED (Federal Reserve Economic Data) to build an accurate and continuously syncing model for the price of gold.

Introducing Passport by Adaptive. Your agent can now sign up for accounts on your behalf and acquire API keys, service credentials, and other things that it might need — without user intervention. Here, it acquires an API key from FRED (Federal Reserve Economic Data) to build an accurate and continuously syncing model for the price of gold.

Adaptive

38,511 次观看 • 4 个月前

Jev builds the MOST POWERFUL trading agents and someone JUST open sourced jev-trader, a fully working 24/7 trading bot with Jev along with COMPLETE low latency CODEBASE WHAT THIS MEANS FOR YOU - you no longer have to build a trading bot with Jev from scratch, you just clone this and make it yours here is how you make your own Jev trading bot with this repo: 1. clone it and run three commands, it boots straight into dry run mode with real book data, real decisions, and simulated fills so you can watch it think with zero capital 2. drop in your Jev API key and the model starts answering buy or sell on every block with calibrated probabilities in 81 milliseconds 3. swap the book reader for your own venue, the model interface is clean so any order book that returns bids and asks plugs straight in 4. tune the decision cadence and horizon, ask the model every N blocks about the move over the next M, so you control how aggressive the engine trades 5. the hot loop already fits one block with exactly two round trips, one to read the book, one to send the order, nothing else on the path, this is the institutional latency discipline most retail bots never reach 6. plug in the live server and every block, every decision, every fill streams to a public dashboard so you watch your engine run the whole point is this repo hands you HARDEST part for FREE - > the low latency engine the COMPLETE breakdown of how i turned this into hedge fund grade HFT trading system is in my article below:

Jev builds the MOST POWERFUL trading agents and someone JUST open sourced jev-trader, a fully working 24/7 trading bot with Jev along with COMPLETE low latency CODEBASE WHAT THIS MEANS FOR YOU - you no longer have to build a trading bot with Jev from scratch, you just clone this and make it yours here is how you make your own Jev trading bot with this repo: 1. clone it and run three commands, it boots straight into dry run mode with real book data, real decisions, and simulated fills so you can watch it think with zero capital 2. drop in your Jev API key and the model starts answering buy or sell on every block with calibrated probabilities in 81 milliseconds 3. swap the book reader for your own venue, the model interface is clean so any order book that returns bids and asks plugs straight in 4. tune the decision cadence and horizon, ask the model every N blocks about the move over the next M, so you control how aggressive the engine trades 5. the hot loop already fits one block with exactly two round trips, one to read the book, one to send the order, nothing else on the path, this is the institutional latency discipline most retail bots never reach 6. plug in the live server and every block, every decision, every fill streams to a public dashboard so you watch your engine run the whole point is this repo hands you HARDEST part for FREE - > the low latency engine the COMPLETE breakdown of how i turned this into hedge fund grade HFT trading system is in my article below:

Roan

44,981 次观看 • 11 小时前

every question in this clip is an ownership question, especially data because when everyone has access to the same intelligence, the only input that separates your business from the next one is the data you own your data is decades of decisions, customers, mistakes, and edge cases that exist nowhere else on earth that is the moat and enterprises are waking up to the fact that they've been leaking it one api call at a time my prediction is this: data ownership is going to absolutely matter in the world we're going into and whoever's building the infrastructure for it is going to have a very good decade.

every question in this clip is an ownership question, especially data because when everyone has access to the same intelligence, the only input that separates your business from the next one is the data you own your data is decades of decisions, customers, mistakes, and edge cases that exist nowhere else on earth that is the moat and enterprises are waking up to the fact that they've been leaking it one api call at a time my prediction is this: data ownership is going to absolutely matter in the world we're going into and whoever's building the infrastructure for it is going to have a very good decade.

Adeniyi.sui

13,834 次观看 • 2 个月前

I'm still picking my jaw off the floor with this MCP update: Postman will now automatically build an MCP server for an API. Automatically! You select your API and the requests you want to include, and Potman will generate a Zip file with everything you need. In collaboration with Postman, I recorded a video showing how I generated an MCP server for the Google Maps API. It's glorious! Also, and before I forget: You can now test any MCP server with your Postman application. They built MCP right in, so now you can: • Connect to an MCP server • List out all of the available tools • Test any of the tools This is a 10x boost for the MCP ecosystem. If you've tried the default MCP debugger, you'll understand how huge a deal it is that you can do all of that from Postman now. Go here to give this a try:

I'm still picking my jaw off the floor with this MCP update: Postman will now automatically build an MCP server for an API. Automatically! You select your API and the requests you want to include, and Potman will generate a Zip file with everything you need. In collaboration with Postman, I recorded a video showing how I generated an MCP server for the Google Maps API. It's glorious! Also, and before I forget: You can now test any MCP server with your Postman application. They built MCP right in, so now you can: • Connect to an MCP server • List out all of the available tools • Test any of the tools This is a 10x boost for the MCP ecosystem. If you've tried the default MCP debugger, you'll understand how huge a deal it is that you can do all of that from Postman now. Go here to give this a try:

Santiago

215,882 次观看 • 1 年前

Tangem Markets 📊 We’ve added a powerful new Markets section to the Tangem Wallet app, bringing you real-time crypto data and insights. Now, you can track live price movements, analyze trends, view key metrics, and manage supported cryptocurrencies—all in one place. No more switching between apps to find the info you need. Watch this video to explore Tangem Markets in more detail.

Tangem Markets 📊 We’ve added a powerful new Markets section to the Tangem Wallet app, bringing you real-time crypto data and insights. Now, you can track live price movements, analyze trends, view key metrics, and manage supported cryptocurrencies—all in one place. No more switching between apps to find the info you need. Watch this video to explore Tangem Markets in more detail.

Tangem

23,326 次观看 • 1 年前

What defines the "Best Chain for AI Agents"? > Infra that keeps up with the Chain. > Integrated Stack for Smooth Integrations. > MultiVM & Native Automation enabling true "On-Chain Super Agents" In this Demo Series, we’ll build AI Agents using Supra Integrated L1 to create powerful AI Agents that redefine the experience, alongside using powerful tools such as OpenBlocks and more... For the Starting, Let’s build an AI Agent that: ✅ Fetch real-time & historical market data from SupraOracles. ✅Compute technical indicators for informed decision-making. ✅Forecast short-term price trends using Facebook's ML Model. ✅Handle follow-up questions to analyze Marketing for a trading pair through OpenAI GPT. Buckle up, time to build Super Agents on Supra! 🤖💪🏻

What defines the "Best Chain for AI Agents"? > Infra that keeps up with the Chain. > Integrated Stack for Smooth Integrations. > MultiVM & Native Automation enabling true "On-Chain Super Agents" In this Demo Series, we’ll build AI Agents using Supra Integrated L1 to create powerful AI Agents that redefine the experience, alongside using powerful tools such as OpenBlocks and more... For the Starting, Let’s build an AI Agent that: ✅ Fetch real-time & historical market data from SupraOracles. ✅Compute technical indicators for informed decision-making. ✅Forecast short-term price trends using Facebook's ML Model. ✅Handle follow-up questions to analyze Marketing for a trading pair through OpenAI GPT. Buckle up, time to build Super Agents on Supra! 🤖💪🏻

Jatin Pandya

13,685 次观看 • 1 年前

Priority Fees tracking is live at Priority fees are HYPE burned to move faster on Hyperliquid. Two separate burns: write priority, where you pay for a taker order to be filled sooner, and read priority, an auction for faster market-data reads. Both fully tracked. What you can track: - Priority fees as a share of all Hyperliquid revenue, and how that share is growing over time - Which markets pay the most priority, and where it rivals or beats the trading fee itself - Daily HYPE burned for priority since launch, in dollars and HYPE, split write vs read - An annualized run-rate you can model yourself, with sliders for priority growth and HYPE price - The wallets paying the most, 24h and all-time, and how concentrated the spend is - The live read auction in real time, and who is winning it right now - Cost per fill, total fills, and the user base growing over time Hyperliquid.

Priority Fees tracking is live at Priority fees are HYPE burned to move faster on Hyperliquid. Two separate burns: write priority, where you pay for a taker order to be filled sooner, and read priority, an auction for faster market-data reads. Both fully tracked. What you can track: - Priority fees as a share of all Hyperliquid revenue, and how that share is growing over time - Which markets pay the most priority, and where it rivals or beats the trading fee itself - Daily HYPE burned for priority since launch, in dollars and HYPE, split write vs read - An annualized run-rate you can model yourself, with sliders for priority growth and HYPE price - The wallets paying the most, 24h and all-time, and how concentrated the spend is - The live read auction in real time, and who is winning it right now - Cost per fill, total fills, and the user base growing over time Hyperliquid.

HL Eco

19,154 次观看 • 2 个月前

You can now connect your React application to any MCP server! And it only takes a single command: $ npx copilotkit@latest init -m MCP This is massive for anyone building React applications! Using the CopilotKit🪁 MCP Client Component, you can get an MCP Client chat component in your application and instant access to any MCP server out there! It doesn't get easier than this. Check out the link below for instructions on how to proceed ↓

You can now connect your React application to any MCP server! And it only takes a single command: $ npx copilotkit@latest init -m MCP This is massive for anyone building React applications! Using the CopilotKit🪁 MCP Client Component, you can get an MCP Client chat component in your application and instant access to any MCP server out there! It doesn't get easier than this. Check out the link below for instructions on how to proceed ↓

Santiago

39,944 次观看 • 1 年前

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:

Santiago

185,640 次观看 • 2 年前