Hi, I'm Aviraj Khare — a decade of shipping software: platform engineering at Gojek, then AI infra and developer tools. Now I train custom models on Apple Silicon and build the harnesses that make AI agents actually work.
Troy fine-tunes LLMs on your Mac. One YAML file becomes a LoRA training run on Apple Silicon — no notebooks, no boilerplate, no GPU rental.
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.
A local MCP server for code intelligence. Keeps coding agents grounded in the real codebase instead of hallucinating one.