TERMy
Dev tools
terminal assistant
SHOW HN2026
225points
45comments
#234of 4,366 in 2026
Top 6%of 2026 by points
How HN took it
LovedMost comments that take a side are positive
12 positive, 12 neutral or asking, 0 mixed, 1 critical, out of 25 comments about the project. Thread score +0.40.
Idea: 9 for, 0 againstDesign: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Deterministic, predictable design that suits a safe terminal tool
From 3 comments
At first blush, it is a really persuasive compromise between full-on LLM inference and boring old fuzzy history search! I really like it, this flavor of specialization gives the…
mpalmer on HNI haven't evaluated it yet, but I love the fact that the output is (at least claimed to be) deterministic. I can't trust an LLM to do the right thing after I deploy it to…
gurjeet on HNThis is a cool project; I think it's wonderful that traditional NLP methods are being used, rather than reaching straight for an LLM. One significant advantage of not using a…
publlus_enigma on HN
Runs fast on CPU without LLM dependencies
From 2 comments
This is a cool project; I think it's wonderful that traditional NLP methods are being used, rather than reaching straight for an LLM. One significant advantage of not using a…
publlus_enigma on HNAt first blush, it is a really persuasive compromise between full-on LLM inference and boring old fuzzy history search! I really like it, this flavor of specialization gives the…
mpalmer on HN
Clever, simple idea applied in a novel way
From 2 comments
I'll be the first to admit I burn too many tokens on the command line. Some form of LLM harness has been my new shell for the past 3+ years, they are much better at *sh then me,…
_superposition_ on HNThis is such a cool project. I can’t wait to try it out.
asa123 on HN
Objections
Limited to predetermined responses, cannot generate text
From 1 comment
Warp uses LLMs so it is slow and prone to hallucination. Using very colloquial terms TERMy is more or less a calculator that knows english :) so it can run on your CPU and…
gioscarab on HN
Sentiment analysis is only a gimmick that adds an emoji
From 1 comment
Ciao, yes for now the sentiment analysis is used only to provide an emoji related to the response. In the future I would like also to influence the choices of adjectives and…
gioscarab on HN
Requests
Fallback to an LLM for unseen or low-confidence queries
From 3 comments
It's kind of antithetical to the tool's deterministic positioning, but have you considered making TERMy leverage an LLM for unseen or low-confidence queries, and then generate…
mbil on HNI like the project. I see a lot of potential integrating it with LLM providers in an effort to lower token usage for repetitive tasks. Your solution becomes the "main model" and…
paguasmar on HNIt would make sense to have this integrate with a self-learning routine for an agent: e.g. at night it looks through what it did and writes NPC-Forge recipes. Tomorrow it can…
dmos62 on HN
Support for coding tasks
From 2 comments
If you could get Termy to code, you'd be a rich man
vegnus on HNThat would be so amazing. Even if it just helped with repetitive or hard to remember patterns.
stefanka on HN
Ask for approval before running potentially destructive commands
From 1 comment
is it supported to have it propose a command for approval rather than running autmatically? in the YT video it looks likw it ran the cpu temp command on its own love the…
cyberclimb on HN
Find installed packages by task
From 1 comment
what I would love to see along those lines is something that can answer "what packages do I have installed to do task $foo"; I keep installing things that I use for one thing and…
zem on HN
Questions
Which dataset does step 5 rely on
From 1 comment
What dataset does step 5 rely on? Is it from your own terminal history, man pages, scrapped dataset from e.g. StackOverflow, sth else?
utopiah on HN
How does it differ from Warp's AI mode
From 1 comment
Cool project! How does it differ from warp terminals ai mode where you can ask it questions and it responds back
registereduser1 on HN
Are there similar datasets for coding
From 1 comment
Any similar data sets for coding?
stefanka on HN
Alternatives named
Warp terminal AI mode
From 2 comments
Cool project! How does it differ from warp terminals ai mode where you can ask it questions and it responds back
registereduser1 on HNWarp uses LLMs so it is slow and prone to hallucination. Using very colloquial terms TERMy is more or less a calculator that knows english :) so it can run on your CPU and…
gioscarab on HN
tldr / tealdeer cheatsheets
From 2 comments
So is this kind of like a super-powered tealdeer ?
indigodaddy on HNYes tldr, navi cheatsheets are essentially a great set of how to do X using Y for terminal utilities. Pretty well curated set of commands for majority of the tasks, so are great…
analog_daddy on HN
nl2bash dataset
From 1 comment
cf. https://github.com/TellinaTool/nl2bash paper: https://arxiv.org/abs/1802.08979
nateb2022 on HN
FunctionGemma and small LLMs
From 2 comments
> Models like ornith:9b, mistral:7b or cogito:14b can get the job done sometimes, but they are not fast and reliable enough for general use, specially if you have only 4GB of…
kouteiheika on HNFunctionGemma never worked well for me (without fine tuning). Liquid has released 230M and 350M models that work far, far better in my testing:…
coder543 on HN