Single bash command to find the best matching HN jobs
Just a clever curl pipe, not a standalone tool or product.

No LLMs — template matching beats stochastic bash generation for reproducibility.
Developers who want reliable shell command generation without LLM variance
Hunch · ShellGenie · Claude Code
ShellTalk is written in Swift and available under the Apache 2.0 license on GitHub. I was inspired a few weeks ago after reading the Meta-Harness paper and seeing a tool called Hunch that did something similar using the Apple Foundation model. I often forget flag names and orders, but I wanted something that worked consistently. The 3B AFM worked surprisingly well with Hunch, but it felt slow and sometimes slight changes in what I wrote would result in very different outputs.
ShellTalk attempts to match the input with an intent category (Git, File I/O, etc), then a template, and finally to slot-fill and adapt to the specific command version and BSD vs GNU syntax. It has a few other tricks including using NSSpellChecker on macOS to auto-correct certain typos, and scores the output on safety (i.e. is the action destructive or non-reversible).
It's clearly far from perfect, but has very tight testing and validation cycles compared to using an LLM, is very portable, and might eventually work in other languages or environments like Windows. I'm curious to hear what others think.
Just a clever curl pipe, not a standalone tool or product.
No-code game bot builder with image matching—community-driven, but ToS risk high.
Solves an unsolved problem: format incompatibility between Claude, GPT, LLaMA documented by research.
Swaps vector databases for filesystem grep to cut costs and improve traceability.
Deterministic graphs instead of vector embeddings sound clever, but long-context windows and RAG tools already solve this problem cheaper.
Pandoc alternative for TROFF that guesses layout from plain text conventions.