Hi, I'm Aviraj Khare — a decade of shipping software, a big chunk of it doing platform engineering at Gojek. Now I fine-tune models on Apple Silicon, build memory for agents, and steer LLMs instead of being steered by them.
Fine-tune LLMs on Apple Silicon from a single YAML file. No notebooks, no boilerplate — describe the run, hit enter.
A local-first memory layer for AI agents. Your agent remembers; your data never leaves the machine.
A working WebAssembly terminal embedded inside a Notion page. Because why not.
Write in Notion, publish on GitHub. It powers the blog on this very site.