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。

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 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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 次观看 • 29 天前

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 次观看 • 1 个月前

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 次观看 • 3 个月前

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 次观看 • 6 个月前

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 次观看 • 17 天前

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 次观看 • 9 个月前

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 🚀

126,213 次观看 • 10 个月前

🔥 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

218,306 次观看 • 12 天前

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 次观看 • 2 个月前

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

21,351 次观看 • 2 个月前

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 次观看 • 7 个月前

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 次观看 • 10 个月前

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

15,224 次观看 • 7 个月前

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 次观看 • 6 个月前

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 次观看 • 4 天前

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 次观看 • 2 个月前

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 次观看 • 8 个月前

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 次观看 • 1 年前

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 次观看 • 1 个月前

Introducing Auto Clips: a new feature that automatically creates Clips based on the best parts of your stream using a variety of signals from the broadcast. You can also pick these moments while streaming by saying “Clip That.” Auto Clips is still in development, and we’ll have more to share on it later this year. Sign up for Alpha access here:

Introducing Auto Clips: a new feature that automatically creates Clips based on the best parts of your stream using a variety of signals from the broadcast. You can also pick these moments while streaming by saying “Clip That.” Auto Clips is still in development, and we’ll have more to share on it later this year. Sign up for Alpha access here:

Twitch

81,681 次观看 • 11 个月前