home.social

#firecrawl — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #firecrawl, aggregated by home.social.

  1. Как научить Claude Code работать с вебом и не сжигать на этом лимиты

    Попросить LLM-агента типа Claude Code "сходи в интернет и собери мне данные" - это как играть в казино. Иногда везет, и ты получаешь то что искал. А иногда сжигаешь половину дневного лимита на двух сайтах, упираешься в антибот защиту и в итоге получаешь кашу из тегов вперемешку с куском нужного контента. Любой, кто пробовал натравить LLM-агента на сайт, знает это чувство: даешь простую задачу - собери данные с такой-то страницы. Агент бодро рапортует, что работа кипит. Проходит минута, две, он пошел по соседним ссылкам, начал сам что-то искать, что-то быстро перебирает, и в итоге половину сайтов он не смог открыть, половина второй половины - это мусор и только крупица нужной информации. В этой статье я предложу вам один способ, которым пользуюсь сам и который хорошо ( почти всегда ) решает эту проблему.

    habr.com/ru/articles/1020598/

    #claude_code #claude_code_skills #mcp #Firecrawl #вебскрапинг #aiагенты #llm #anthropic #вебпоиск

  2. 🎯 Supported models include #GPT-OSS-120B, #GPT-OSS-20B, #Llama4 Maverick, #Llama4 Scout, #Llama33-70B, #Llama31-8B, #KimiK2, #Qwen3-32B

    🔧 Key features: deterministic inference for faster tool-using agents, cost-effective scaling, approved tool use with clear allowlists, seamless migration capability

    📋 Ready-to-use cookbook tutorials with #BrowserBase #MCP, #BrowserUse #MCP, #Exa #MCP, #Firecrawl #MCP, #HuggingFace #MCP, #Parallel #MCP, #Stripe #MCP, #Tavily #MCP

  3. Making the most out of a small LLM

    Yesterday i finally built my own #AI #server. I had a spare #Nvidia RTX 2070 with 8GB of #VRAM laying around and wanted to do this for a long time.

    The problem is that most #LLMs need a lot of VRAM and i don't want to buy another #GPU just to host my own AI. Then i came across #gemma3 and #qwen3. Both of these are amazing #quantized models with stunning reasoning given that they need so less resources.

    I chose huihui_ai/qwen3-abliterated:14b since it supports #deepthinking, #toolcalling and is pretty unrestricted. After some testing i noticed that the 8b model performs even better than the 14b variant with drastically better performance. I can't make out any quality loss there to be honest. The 14b model sneaked in chinese characters into the response very often. The 8b model on the other hand doesn't.

    Now i've got a very fast model with amazing reasoning (even in German) and tool calling support. The only thing left to improve is knowledge. #Firecrawl is a great tool for #webscraping and as soon as i implemented websearching, the setup was complete. At least i thought it was.

    I want to make the most out of this LLM and therefore my next step is to implement a basic #webserver that exposes the same #API #endpoints as #ollama so that everywhere ollama is supported, i can point it to my python script instead. This way it feels like the model is way more capable than it actually is. I can use these advanced features everywhere without being bound to it's actual knowledge.

    To improve this setup even more i will likely switch to a #mixture_of_experts architecture soon. This project is a lot of fun and i can't wait to integrate it into my homelab.

    #homelab #selfhosting #privacy #ai #llm #largelanguagemodels #coding #developement

  4. #Firecrawl, an #opensource #webcrawler for #developers and #AIagents, raised $14.5 million in a Series A round led by Nexus Venture Partners. The company, which is already profitable, plans to use the funds to expand its team and develop tools to help website owners get paid when AI uses their content. techcrunch.com/2025/08/19/ai-c #Pirates #Tech #Startup #News