Mark McD ☠
@m4rkmc
I do ♊ Gemini DevRel at @GoogleDeepMind. 100% remote. (but I speak for myself, surprisingly they dont want my tweets 🤷♂)
I am PUMPED to finally share what we’ve been working on: 🖥️ Introducing the Gemini CLI! It can code, sure, but with access to your system shell, files and MCP servers, it can also: 👩🔬 Do research 💽 Organise your MP3s Resolve rebases 🔬 Even strace that weird hung process…
Good morning #Bengaluru 🌟 Today's the day for #IOConnect so drop by my demo station booth throughout the day to pick up some swag and see the latest #WebAI agentic demos running entirely client side in your web browser! Yep agents with total privacy, no inference cost, and low…
What should we add next to Gemini CLI’s MCP support? 👇
Thought completer 💭⚡️ Real-time screencap testing speed of Gemini 2.5 Flash-Lite. So neat to be able to access so much knowledge in under a second. Link in 🧵
The oss community around Gemini CLI has been incredible, SO many thoughtful PRs coming in so we've been exploring ways to scale triage, including using Gemini CLI to triage itself. Wildly meta, but also wildly useful. Thought I’d share my workflow this afternoon, so I recorded a…
🚀 Introducing context42 The best code style guide is the one your team already follows. This tool discovers it. context42 explores your codebase using Gemini CLI and conjures up custom style guides for every language it finds.
Well that is how gold medals work. (ikik it's a joke)
Such bs. The majority of math majors or even math phds and faculty could not win a gold in imo.
Build powerful resume agents with our new @crewAIInc and Gemini 2.5 quickstart, using built-in grounding with Google Search to power your Crew with a single API key. In the example: 🔎 Research your public GitHub profile 🔬 Deep dive into your projects 📝 Write a custom CV
Please. You can drive almost 40hrs without leaving Western Australia.
You can drive 14 hours without leaving Germany
🇮🇳 Devs are you attending @Google IO Connect? @GoogleDeepMind DevRel is coming to Bengaluru on July 23rd and! Join @film_girl @ptruiz_dev @osanseviero @m4rkmc on technical sessions, workshops and experience the latest demos. Hear about Gemini @googleaistudio Gemma @geminicli🚀👀
📣 Gemini CLI roadmap It has been so cool seeing everyone building with the Gemini CLI (60k ⭐s!), and sharing feedback (1k open issues 😬) To make things even more transparent the team has made the 🗺️ roadmap public. Take a look and tell us what you think:…
Our first Gemini Embedding text model (gemini-embedding-001) is now GA and #1 on the MTEB leaderboard 🙂 Give it a go and let us know what you think! Read more: developers.googleblog.com/en/gemini-embe…
Next week we're doing an Open Models Meetup in Bangalore and we're looking for speakers! Speakers include team members from Google DeepMind, so you'll hear about Gemma, synthetic data, and architectural evolutions. See you there! Call for Speakers👉 forms.gle/zrWN95Cspmtby4…
Gemini CLI key highlights for week of 7/7/2025 - Nightly builds can be installed with npm i -g @google/gemini-cli@nightly - Paste images with ctrl + v (jasondasher) - SVG support (PugazhendhiDev) - Better markdown tables (zfflxx) - Configurable headers for SSE MCP servers…
This is beautiful.
Yesss! 😸 *This* is the behavior I was looking for. Of course this is for streaming Markdown from an LLM. Exciting, no? #Python #AI
Excited to introduce GenAI Processors! An Open-Source Python library from @GoogleDeepMind that allows you to build asynchronous and composable AI Pipelines for Generative AI
In order to supervise an automation tool (or another person!) effectively, you need to be able to do the same job yourself. Doesn't matter if you rarely ever do the job yourself (like a manager who no longer codes), you need to be *able* to do it.
what almost every amateur who has been sold bullshit about vibe coding is eventually going to encounter