- SignalDesk4 hr ago
Original Summary
onesie is a Unix-style CLI for using System One models in shell pipelines, scripts, and agentic workflows: <a href="https://github.com/frodi-karlsson/onesie" rel="nofollow">https://github.com/frodi-karlsson/onesie</a><p><pre><code> echo 'EVERYTHING IS DOWN, CALL ME NOW' | onesie 'does this convey urgency' -r # 0.99 </code></pre> It provides caching, batching, deduplication, unix composability, streaming, and even a way to calibrate thresholds and questions against labelled data:<p><pre><code> onesie calibrate -f shell-safety -i jsonl --map .command --id .id \ --label destroys=.destroys --label secrets=.secrets --label network=.network \ --cuts 0.25,0.5 < examples/data/shell-safety.jsonl destroys, yes/no: labelled 40, 16 yes, 24 no, 0 failed. AUC 1.00 cut flagged catches false alarms right when flagged 0.25 18 16/16 100% 81-100% 2/24 8% 2-26% 16/18 89% 67-97% 0.50 15 15/16 94% 72-99% 0/24 0% 0-14% 15/15 100% 80-100% worst misses echo-overwrite labelled yes answered 0.37 </code></pre> It works with TypeSafe's Jev, Jev via OpenRouter, Berget's System One models, as well as any Jev-compatible APIs.<p>For anyone unaware, System One is Typesafe's term for a class of models. I personally find them super exciting. You can read more here: <a href="https://typesafe.ai/blog/introducing-system-one-models-and-jev" rel="nofollow">https://typesafe.ai/blog/introducing-system-one-models-and-j...</a>.<p>When Jev launched, one of my first toy projects was using it to "lint" files. It was tough, and I found other people doing it better, but I learned the importance of calibrating questions to minimize false negatives/positives.<p>Later I started using scripts to interface with Jev and found myself wanting some features I couldn't find in other CLIs, so I built onesie. Here are some more examples of what onesie can do:<p>Ask three questions in a single request<p><pre><code> echo 'Third time asking. I was charged twice and nobody answers. Fix it or I am cancelling.' | onesie --ask urgent='is this urgent' \ --ask team='who should handle this' --pick billing,shipping,technical \ --ask mood='how frustrated is the customer' --rate calm,annoyed,furious \ -o values {"urgent":0.91,"team":"billing","mood":"furious"} </code></pre> Filter streamed log entries for human review<p><pre><code> tail -f app.log | onesie 'does this line report a failure a person must act on' -i lines --merge -o json \ --assert 'answer.value < 0.8' | jq -c --unbuffered 'select(.answers.assert == false)' </code></pre> Gate the command in a script. A failed gate exits 1, and an uncertain one exits 7. Note: Probably don't run this exact gate on user input in prod.<p><pre><code> echo "$cmd" | onesie -f shell-safety -q case $? in 0) eval "$cmd" ;; 1) echo blocked ;; 7) ask_the_user ;; *) echo 'no answer, blocked' ;; esac </code></pre> ... And many more. Please check out the repo for more examples and a detailed reference!<p>It's obviously hard to try out onesie without an api key for a Jev-like provider, although there are options for using mock data or dry-running. There are instructions in the repo for how to auth with a key.<p>If you want an MCP server or a cost estimate before each run, shaharia-lab/jev-cli has both. It's a nice project.<p>I opted out of an MCP server because my intended audience is people and local agentic workflows. For these, I'm of the opinion that a good CLI is best, especially when combined with a plugin + skills. I also felt most of onesie's standout features aren't well served by the protocol. There are other dedicated Jev MCPs out there that do just fine.<p>I opted out of cost estimates because I'm not interested in estimating tokens or keeping a table of costs up to date when the models are so cheap.<p>You can install it with<p><pre><code> brew install frodi-karlsson/tap/onesie </code></pre> or<p><pre><code> go install github.com/frodi-karlsson/onesie/cmd/onesie@latest </code></pre> And yes, development has been very agentic :)<p>It's MIT-licensed.
- 情报分类：服务器与云资源
- 分类依据：内容涉及服务器、云资源或网络线路
- 信息来源：Hacker News 新项目
- 发布时间：2026/9/28 19:37:25
- No replies yet