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 our most accurate /search yet. We trained a model to return the excerpts that best answer your query, giving agents highly relevant context from each result. It's SOTA on SimpleQA while using 10x fewer tokens than processing full pages. Now on by default for free.

Firecrawl

84,866 subscribers

37,248 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing the official Firecrawl connector for Claude 🔥 Add state-of-the-art web search to your AI agents (94.7% on SimpleQA). Powered by our live indexes for fresher results across research, the open web, and more. Live in the Anthropic connector directory now!

Introducing the official Firecrawl connector for Claude 🔥 Add state-of-the-art web search to your AI agents (94.7% on SimpleQA). Powered by our live indexes for fresher results across research, the open web, and more. Live in the Anthropic connector directory now!

Firecrawl

90,406 views • 1 month ago

Introducing the Firecrawl plugin for Codex. Give Codex access to the most accurate search available (94.7% on SimpleQA) plus tools to scrape, crawl, and interact with any site. Find us on the OpenAI plugin marketplace today!

Introducing the Firecrawl plugin for Codex. Give Codex access to the most accurate search available (94.7% on SimpleQA) plus tools to scrape, crawl, and interact with any site. Find us on the OpenAI plugin marketplace today!

Firecrawl

85,264 views • 1 month ago

Today we're releasing Monitoring by Firecrawl 📡 Just enter a URL, describe what you want to track, and /monitor notifies your AI agent via webhook the moment pages or sites change. Use up to 90% fewer LLM tokens by only ingesting what changes on a page.

Today we're releasing Monitoring by Firecrawl 📡 Just enter a URL, describe what you want to track, and /monitor notifies your AI agent via webhook the moment pages or sites change. Use up to 90% fewer LLM tokens by only ingesting what changes on a page.

Firecrawl

101,256 views • 3 months ago

The Firecrawl plugin is now available in OpenCode 🔥 $ npm install -g firecrawl-cli Let agents scrape, search, and browse the web for real-time context - right from your terminal.

The Firecrawl plugin is now available in OpenCode 🔥 $ npm install -g firecrawl-cli Let agents scrape, search, and browse the web for real-time context - right from your terminal.

Firecrawl

41,734 views • 6 months ago

Firecrawl is now available in Grok Bot 🔥 Turn the web into high-quality context for your Grok Bot, powered by industry-leading search and scraping designed for agents. Install the Firecrawl plugin to get started!

Firecrawl is now available in Grok Bot 🔥 Turn the web into high-quality context for your Grok Bot, powered by industry-leading search and scraping designed for agents. Install the Firecrawl plugin to get started!

Firecrawl

22,965 views • 24 days ago

Introducing the Firecrawl Connector for Lovable 🔥 Your Lovable apps can now scrape, search, and crawl the web out of the box powered by Firecrawl. Free for all users for a limited time! Try it out today 👇

Introducing the Firecrawl Connector for Lovable 🔥 Your Lovable apps can now scrape, search, and crawl the web out of the box powered by Firecrawl. Free for all users for a limited time! Try it out today 👇

Firecrawl

15,864 views • 9 months ago

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Akshay 🚀

126,250 views • 10 months ago

🔥 GLM-5.3-Flash Hits #1 on 🐮 GLM-5.3-Flash (Ox Alpha) is now the most-used and most popular model on with cumulative token throughput surpassing 2.41 trillion tokens. As the first native omni-modal model in the GLM-5 series, it packs 320B total parameters, with 18B active, and features a hybrid sparse and linear attention architecture with a 1M-token context window. The result: lightning-fast responses, powerful reasoning, and outstanding cost efficiency. 🎁 Still 100% FREE on From high-frequency API calls and coding to complex Agents and long-document processing, jump in and experience the #1 model on for yourself! 👉 Try it free now:

🔥 GLM-5.3-Flash Hits #1 on 🐮 GLM-5.3-Flash (Ox Alpha) is now the most-used and most popular model on with cumulative token throughput surpassing 2.41 trillion tokens. As the first native omni-modal model in the GLM-5 series, it packs 320B total parameters, with 18B active, and features a hybrid sparse and linear attention architecture with a 1M-token context window. The result: lightning-fast responses, powerful reasoning, and outstanding cost efficiency. 🎁 Still 100% FREE on From high-frequency API calls and coding to complex Agents and long-document processing, jump in and experience the #1 model on for yourself! 👉 Try it free now:

B.AI

222,236 views • 20 days ago

Perplexity users can now onramp crypto powered by the MoonPay Model Context Protocol (MCP) get started in seconds on Perplexity using our new Custom Connector to give your agents access to crypto here's a look at how it works:

Perplexity users can now onramp crypto powered by the MoonPay Model Context Protocol (MCP) get started in seconds on Perplexity using our new Custom Connector to give your agents access to crypto here's a look at how it works:

MoonPay 🟣

56,550 views • 2 months ago

Introducing /monitor for Slack - get pinged the moment a page, site, or the web changes 📡 Our always-on AI agents scan the web around the clock and drop alerts right in your Slack channels. Just create a monitor on the dashboard, then click "Receive alerts in Slack."

Introducing /monitor for Slack - get pinged the moment a page, site, or the web changes 📡 Our always-on AI agents scan the web around the clock and drop alerts right in your Slack channels. Just create a monitor on the dashboard, then click "Receive alerts in Slack."

Firecrawl

21,793 views • 2 months ago

Introducing Branding Format v2 🎨 Our endpoint for extracting brand identities from the web just got a lot better. - Works with sites built on Wix, Framer, and other no-code builders - Fewer false positive logo extraction - Handles logos hidden in bg images Try it below 👇

Firecrawl

57,111 views • 7 months ago

Introducing the Branding format 🎨 You can now extract complete brand DNA from any website including color schemes, logos, frameworks and more in one API call Perfect for coding agents to clone or match existing site aesthetics. Try it out now on the playground or API today 👇

Firecrawl

111,093 views • 10 months ago

Tavily Agent Skills are now here ⚡ Your agents can now: search the live web pull fresh docs & pages research markets, competitors and products cite sources all without leaving the terminal. We also shipped tavily-best-practices. A skill that teaches agents how to build production-ready web-connected AI built on real-world lessons from builders like you. Works wherever you’re building agents: Claude · Cursor · Google Antigravity Install now with one line.

Tavily Agent Skills are now here ⚡ Your agents can now: search the live web pull fresh docs & pages research markets, competitors and products cite sources all without leaving the terminal. We also shipped tavily-best-practices. A skill that teaches agents how to build production-ready web-connected AI built on real-world lessons from builders like you. Works wherever you’re building agents: Claude · Cursor · Google Antigravity Install now with one line.

Tavily

15,286 views • 7 months ago

Wikipedia is one of the most requested sources on Firecrawl. So we partnered with Wikimedia Enterprise 🤝 Users now get faster responses and cleaner, structured data - while Firecrawl directly contributes to the infrastructure that keeps Wikipedia running.

Wikipedia is one of the most requested sources on Firecrawl. So we partnered with Wikimedia Enterprise 🤝 Users now get faster responses and cleaner, structured data - while Firecrawl directly contributes to the infrastructure that keeps Wikipedia running.

Firecrawl

10,623 views • 6 months ago

this is f*cking gold engineers at Meta just deleted the most expensive part of multi-agent systems: instead of training a communication topology, they compile a fresh one for every query 20 agents went from 7 hours to 6 minutes. the problem everyone hits: 5 agents works. 20 agents turns into a group chat that answers slower than one model and costs more than the task is worth. ReActNet's fix is that the graph is written per query, not learned once: > an LLM controller reads the query and the agent roster > it compiles a sequence of directed graphs, one per reasoning stage > every edge carries a written instruction, e.g. "list boundary cases for this behavior" > each agent updates its state from its own previous state plus assigned neighbors > a final node aggregates all five states into the answer > no RL, no gradients, no training stage at all what that buys on gpt-4o: 92.75 average across 6 benchmarks, best on 5 of them. 100.00 on MultiArith. 92.74 pass@1 on HumanEval, +21 over a single model. and the number that should worry anyone running a swarm: at 20 agents GPTSwarm needs 412 minutes and $41.42. ReActNet needs 6.22 minutes and $6.53 and scores higher. the honest catch: more agents did not make it smarter. 5 agents scored 79.74, 20 scored 77.77. the topology was never the thing to learn.

this is f*cking gold engineers at Meta just deleted the most expensive part of multi-agent systems: instead of training a communication topology, they compile a fresh one for every query 20 agents went from 7 hours to 6 minutes. the problem everyone hits: 5 agents works. 20 agents turns into a group chat that answers slower than one model and costs more than the task is worth. ReActNet's fix is that the graph is written per query, not learned once: > an LLM controller reads the query and the agent roster > it compiles a sequence of directed graphs, one per reasoning stage > every edge carries a written instruction, e.g. "list boundary cases for this behavior" > each agent updates its state from its own previous state plus assigned neighbors > a final node aggregates all five states into the answer > no RL, no gradients, no training stage at all what that buys on gpt-4o: 92.75 average across 6 benchmarks, best on 5 of them. 100.00 on MultiArith. 92.74 pass@1 on HumanEval, +21 over a single model. and the number that should worry anyone running a swarm: at 20 agents GPTSwarm needs 412 minutes and $41.42. ReActNet needs 6.22 minutes and $6.53 and scores higher. the honest catch: more agents did not make it smarter. 5 agents scored 79.74, 20 scored 77.77. the topology was never the thing to learn.

NO1ennn

26,237 views • 11 days ago

We're launching 5x faster document parsing in the Firecrawl MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!

We're launching 5x faster document parsing in the Firecrawl MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!

Firecrawl

47,432 views • 3 months ago

You can summarize any webpage with Firecrawl 🔥 Perfect for research, content curation, or building AI agents that need quick context! Try it out in our Playground, SDK, or your favorite no-code automation platform!

You can summarize any webpage with Firecrawl 🔥 Perfect for research, content curation, or building AI agents that need quick context! Try it out in our Playground, SDK, or your favorite no-code automation platform!

Firecrawl

13,731 views • 8 months ago

Stake $OVR, Earn $UOMI – Staking Launches on December 10th The $OVR staking program is coming exclusively on Base on December 10th, giving you the opportunity to earn daily $UOMI rewards by staking your $OVR tokens. 🔹 How to get started: - Buy $OVR on Base or bridge your tokens from Ethereum to Base using a trusted bridge: - Be among the first to stake your $OVR and maximize your share of the $UOMI rewards pool. With no lock-up periods, you’ll maintain full control of your tokens while earning rewards daily. Mark your calendar and get ready to be part of the future of decentralized AI. Stay tuned for more details! 👀

Stake $OVR, Earn $UOMI – Staking Launches on December 10th The $OVR staking program is coming exclusively on Base on December 10th, giving you the opportunity to earn daily $UOMI rewards by staking your $OVR tokens. 🔹 How to get started: - Buy $OVR on Base or bridge your tokens from Ethereum to Base using a trusted bridge: - Be among the first to stake your $OVR and maximize your share of the $UOMI rewards pool. With no lock-up periods, you’ll maintain full control of your tokens while earning rewards daily. Mark your calendar and get ready to be part of the future of decentralized AI. Stay tuned for more details! 👀

Over the Reality 🌐

155,324 views • 1 year ago

Laguna S 2.1 performs at GLM-5.2 level on building popular games with 6x fewer params! We gave three local models the same task: build three popular arcade games that play themselves. Each game is one self-contained HTML file with a bot that plays it. Prompts: – Geometry Dash – Doodle Jump – Air Hockey Outputs: Laguna S 2.1: 10.3K tokens GLM-5.2: 26.4K tokens Hy3: 10.4K tokens Laguna held its quality against a 753B model. We think Laguna's Geometry Dash looked the best of the three, the cube clears every spike and block. GLM won Air Hockey. Its table looked the most detailed of all. Hy3 was the only model that added shooting to its Doodle Jump. But Laguna is the only model in our benchmark that runs on a MacBook with 128GB!

Laguna S 2.1 performs at GLM-5.2 level on building popular games with 6x fewer params! We gave three local models the same task: build three popular arcade games that play themselves. Each game is one self-contained HTML file with a bot that plays it. Prompts: – Geometry Dash – Doodle Jump – Air Hockey Outputs: Laguna S 2.1: 10.3K tokens GLM-5.2: 26.4K tokens Hy3: 10.4K tokens Laguna held its quality against a 753B model. We think Laguna's Geometry Dash looked the best of the three, the cube clears every spike and block. GLM won Air Hockey. Its table looked the most detailed of all. Hy3 was the only model that added shooting to its Doodle Jump. But Laguna is the only model in our benchmark that runs on a MacBook with 128GB!

atomic.chat

66,917 views • 2 months ago

Boom! Grok Tasks Make It One Of The Most POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3

Boom! Grok Tasks Make It One Of The Most POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3

Brian Roemmele

152,242 views • 8 months ago