Tomás Murúa

🇧🇷🇨🇱 Developer Advocate

[Tomás Murúa @tomas_muruap]

@sofia_haze_g @serp_api @lmstudio Here is the documentation if you want to see more examples on how to use the JSON restrictor https://t.co/1Kb5ZFhvNy

[Tomás Murúa @tomas_muruap]

@sofia_haze_g @serp_api @lmstudio It doesn't decide on the fly. I picked a fixed set of fields for each tool based on its API response, and the json_restrictor trims the response server-side before the model ever sees it. The image shows an example where I keep the summary, knowledge graph, and news results

[Tomás Murúa @tomas_muruap]

@DantheRdz @serp_api @lmstudio Just LM Studio right now. The chat and tool-calling run through an OpenAI-compatible endpoint that Ollama also supports, but the app also uses LM Studio's native API to load and unload models, so Ollama would need a small adapter. Doable down the line, just not built yet.

[Tomás Murúa @tomas_muruap]

@sophwave5_4 @serp_api @lmstudio Hi there, I'm the author of the article. Any model with tool calling can work, but it helps to pick one built for agentic workflows since the whole loop leans on that. Qwen3.5-9B is what I used and it runs comfortably; Gemma 4 is another strong option depending on your hardware.

[SerpApi @serp_api]

Introducing SerpTrail, a brand new Open Source SEO and GEO tracker from SerpApi.

📍Track keywords and websites across locations in Google Search and AI Overviews
📊Compare historical performance with saved views
💬Ask questions about past data and live rankings with an OpenAI-powered assistant

https://t.co/v3MYkdd3qP

[Tomás Murúa @tomas_muruap]

@strzibnyj What did you do? 🫪

[Michael Plunkett @MichaelPlunkett]

AGI has been achieved at @ATT support

[Josef Strzibny @strzibnyj]

Nice post from my colleague @tomas_muruap on LM Studio. I think I should start working more with local models too 😅

[Tomás Murúa @tomas_muruap]

Very happy with this blog that I wrote giving a local LLM real-time web search with @lmstudio + @serp_api, running entirely on your own hardware. Local LLMs keep getting more relevant, and being able to plug them into live data is a big part of why.

[SerpApi @serp_api]

Your local LLM stops knowing things the day its training ended.

Here's how to give any model in @lmstudio real-time web search with SerpApi, all on your own hardware. It calls Google Search, Finance, News, Maps, and Flights, and our JSON Restrictor trims a 46K-token response down to ~260 so it fits a small context window.

Read more: https://t.co/vlrG1ek1Ci

[james hawkins @james406]

seriously be careful out there everyone

i had 2 Microsoft Copilot licenses in my car, and someone broke in and left 4 more

[SerpApi @serp_api]

Brazilian PyCon gathering at our booth #427🇧🇷

[Josef Strzibny @strzibnyj]

Breakfast time in Long Beach before PyCon (I am trying to increase my calorie intake to feel like a local)

[Wise @trikcode]

I DIDN'T KNOW YOUR GAME

I. APOLOGIZE. SINCERELY

[SerpApi @serp_api]

Nerdearla Chile 2026 🇨🇱 was an incredible experience!

We were proud to be a sponsor this year. Our developer advocate had a great time connecting with so many developers, engineers, and tech enthusiasts from across the Latin American community.

Thank you to the @nerdearla team for having us. Already looking forward to the next one!

[Magee Clegg @mageeclegg]

people don’t realize Chile 🇨🇱 looks like this...

[#nerdearla @nerdearla]

Queremos agradecer a @serp_api, nuestro Sponsor Bronze, por hacer posible el evento gratuito de tecnología más grande en español 🚀

🔜 #Nerdearla Chile 🇨🇱

📲 16 de abril: charlas virtuales
📆 17 y 18 de abril: evento presencial en @centroGAM + streaming para todo el mundo

¡Inscríbete ahora! ➡️ https://t.co/BVMFWjNYs4

[Ayaan 🐧 @twtayaan]

My Spotify Playlist

[Coder girl 👩‍💻 @dev_maims]

Vibe coder writing books in future

[Tomás Murúa @tomas_muruap]

@strzibnyj Ghostty!!