GoKawiilDeveloper builds LLM-free terminal assistant called TERMy, creator of PJON protocol
The developer behind the PJON networking protocol spent two months building TERMy, a natural-language terminal assistant that avoids using large language models entirely. The project began as an attempt to train small transformer models from scratch on aging consumer hardware, including a GTX 1050 Ti and an i7-4790K, but those experiments produced incoherent or unsettling text outputs.
GoKawiil's interpretation of the reporting above, not reported fact.
The project pushes back against the assumption that useful natural-language interfaces require massive, expensive models running on cloud infrastructure. As AI subscription costs rise, tools like TERMy suggest there is room for lightweight, locally-run alternatives for narrow, repetitive tasks like shell commands.
- TERMy is a terminal assistant built without relying on large language models
- Its creator trained small transformer models from scratch on decade-old consumer hardware
- Early generative model experiments produced unreliable, often bizarre text output
NVIDIA GeForce RTX 4060 Graphics Card — If reading about someone training a model from scratch on an old GTX 1050 Ti makes you want to try it yourself, an RTX 4060 is a friendly modern upgrade for a home tinkering rig. It slots into a standard desktop and gives you far more headroom for CUDA experiments, local training runs, and everything else your dev box does between projects.
See NVIDIA GeForce RTX 4060 Graphics Card on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: github.com, 2026-09-04
Published there as: “Show HN: TERMy – A fast terminal assistant that does not use LLMs”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.