How Shubham thinks
Unified API across devices
Provides a single API that runs on every major device and persists a layered memory graph across sessions.
For you: You can integrate any app with one endpoint, no device‑specific code needed.
Local free AI tools
Turns Google’s Embedding Gemma 2 into a super‑fast, fully‑local, free macOS AI notetaker.
For you: You can run speech‑to‑text on your laptop without cloud fees.
Open‑source community building
His GitHub repo has 140k+ stars, 100+ agents, 20k+ forks, driven by community contributions.
For you: You can leverage a huge library of ready‑made agents and skills for free.
Ask this first
- How does your unified API handle memory across devices?
- What challenges did you face making Gemini 2 local and free?
- Can I contribute a new agent skill to Awesome LLM Apps?
Shubham's brain
Recently updated
In October 2026 I announced a unified AI Agent platform that works via a single API, runs on every major device, and persists a layered…
In early October 2026 I used my X account @Saboo_Shubham_ to announce that Google’s Embedding Gemma 2 model had been repurposed into a…
I just shipped a FREE crash course on building AI agents without writing a single line of code 🤯 In 20 minutes, I take one problem through…
In September 2026 I posted a series of LinkedIn updates highlighting a toy‑scale expert‑router model, new Gemini 3.x live models, the…
In September 2026 I posted a series of LinkedIn updates showcasing a wave of open‑source AI‑agent projects. I highlighted the massive…
In October 2026 I shared a masterclass workflow for building, testing, and governing AI coding agents. I start by finding a working example…