New tool gives CLIs a warm and GUI feeling instead 50%

By Brandon Vigliarolo43%

7/7/2026, 4:30:00 PM

BS Summary: This article contains 25 faulty reasoning types, including Appeal to Authority, Optimism Bias, and Hasty Generalization, with Attempt to Sell a Product or Service as the most egregious example at 24.7% saturation with 175 hits. Analysis detected 1,414 faulty-reasoning hits from 708 analyzed words, generating a BS Score of 50.1% and a BS Rank of 50% (10,710 of 21,168 articles). This article is better (less manipulative) than 50.60% of the article peer group.

Using command-line tools is often the best way to get something done, but remembering all those flags is a chore. 
Now, you can let a simple open-source CLI module turn any command into a GUI for you instead. 
That’s the solution Jordanian full-stack software engineer Omar Soutari built for his first entry into the FOSS community and released this week. 
Instagui, as he calls it, parses CLI tools’ help documentation, makes an API call to Claude to digest it, and then renders the whole thing as a locally hosted web interface that launches in a user’s default browser. 
“I could never remember ffmpeg's flags,” Soutari told The Register in an email when asked why he built Instagui. 
“I'd google the same conversion command for the tenth time and  I realized the information a GUI needs is already sitting in every tool's --help output; someone just has to read it.” 
Soutari’s solution? 
Make Claude do the reading for him, have it design a JSON schema and assemble the web app that’d run on top of the CLI automatically, and then publish it for everyone to use. 
If you’re wondering why Soutari reinvented the wheel already built by tools like Gooey, a Python library that converts Python 3 console programs into GUIs without the use of AI, Soutari told us that Gooey has a number of limitations he wanted to overcome. 
Sure, it creates an actual desktop app, and relies on ground truth established from a Python CLI’s use of the argparse library, but it requires developers to add their own decorator to ensure Gooey can actually read their code. 
That's accurate, but it won’t work in all circumstances. 
“Instagui works from the outside: it reads the --help text of any binary, in any language, with zero changes,” Soutari explained. 
In other words, as long as the help text is complete and well-written, it’ll produce a solid schema that is likely to function well. 
Soutari told us that he knew bad help text was a possibility that could hobble Instagui, so he designed for it: Results get validated against a strict schema, and the tool ships with several pre-verified bundled schemas (ffmpeg, yt-dlp, and pandoc) for use and review as well. 
That, and the JSON schemas Instagui produces are reviewable, and can be edited to make corrections for any of Claude’s mistakes. 
He also noted that Instagui’s interface shows the CLI as the web app runs, serving as a teaching tool instead of just a way to abstract away from the command line. 
As for whether Instagui can be trusted (Soutari admitted Claude Code did most of the work while he supervised), Soutari told us that he designed it to be as local, isolated, and reviewable as possible to ensure it runs safely. 
“Commands execute via an argument array with no shell (so form input can't inject), the server binds to localhost only, state-changing requests are origin-checked, and the exact command is always displayed before it runs,” Soutari told us. 
“It was built with a threat model, not just vibes.” 
Given that Instagui relies on API calls to Claude to generate new schemas, it doesn’t run for free (the tool itself is FOSS, though), but Soutari did his best to ensure that it doesn’t eat up tokens like other AI applications. 
When running the command to capture a new help file into a JSON schema, Instagui makes a Claude API call, but once it creates the schema, that’s that - it stores the file for future use, meaning additional runs of the Instagui web app for that CLI app are done without cost. 
“The bundled tools work with no API key at all, cached tools never re-pay, and the AI call is once-per-tool pennies - I didn't want a tool that meters you,” Soutari explained. 
The Instagui dev told us that he’d welcome additional schema contributions to his app, and intends to include more in future releases as well. 
“I'd love the common-tools library to be community-grown so the AI call becomes the rare path rather than the default,” Soutari told us. 
Instagui (version 0.1, so it might have some bugs, Soutari admits) is available now on GitHub. 
® 
Article reasoning-pattern comparisonThis article: 4.7%Brandon Vigliarolo: 5.3%The Register: 3.3%Confirmation Bias4.7%This article: 6.2%Brandon Vigliarolo: 1.2%The Register: 1.1%Anchoring Bias6.2%This article: 2.8%Brandon Vigliarolo: 2.9%The Register: 3.2%Availability Heuristic2.8%This article: 0.0%Brandon Vigliarolo: 0.4%The Register: 1.0%Representativeness Heuristic0.0%This article: 0.0%Brandon Vigliarolo: 0.1%The Register: 1.3%Hindsight Bias0.0%This article: 3.5%Brandon Vigliarolo: 1.6%The Register: 2.4%Overconfidence Bias3.5%This article: 4.0%Brandon Vigliarolo: 6.9%The Register: 5.1%Framing Effect4.0%This article: 11.2%Brandon Vigliarolo: 1.2%The Register: 0.7%Loss Aversion11.2%This article: 2.8%Brandon Vigliarolo: 0.9%The Register: 0.8%Status Quo Bias2.8%This article: 5.8%Brandon Vigliarolo: 0.2%The Register: 0.2%Sunk Cost Effect5.8%This article: 23.6%Brandon Vigliarolo: 2.0%The Register: 3.1%Optimism Bias23.6%This article: 0.0%Brandon Vigliarolo: 4.5%The Register: 2.6%Pessimism Bias0.0%This article: 0.0%Brandon Vigliarolo: 5.4%The Register: 8.0%Negativity Bias0.0%This article: 1.4%Brandon Vigliarolo: 0.7%The Register: 2.0%Self-Serving Bias1.4%This article: 0.0%Brandon Vigliarolo: 0.6%The Register: 0.8%Fundamental Attribution Error0.0%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.1%Actor-Observer Bias0.0%This article: 6.2%Brandon Vigliarolo: 0.4%The Register: 0.3%In-Group Bias6.2%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.3%Out-Group Homogeneity Bias0.0%This article: 4.4%Brandon Vigliarolo: 0.8%The Register: 1.4%Halo Effect4.4%This article: 0.0%Brandon Vigliarolo: 0.1%The Register: 0.1%Horn Effect0.0%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.1%Dunning-Kruger Effect0.0%This article: 7.9%Brandon Vigliarolo: 2.1%The Register: 1.8%Recency Bias7.9%This article: 3.4%Brandon Vigliarolo: 0.1%The Register: 0.3%Primacy Effect3.4%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.1%Blind-Spot Bias0.0%This article: 0.0%Brandon Vigliarolo: 1.5%The Register: 0.6%Ad Hominem0.0%This article: 0.0%Brandon Vigliarolo: 0.5%The Register: 0.2%Straw Man0.0%This article: 23.7%Brandon Vigliarolo: 3.7%The Register: 4.2%Appeal to Authority23.7%This article: 1.4%Brandon Vigliarolo: 1.0%The Register: 1.7%False Dilemma1.4%This article: 0.0%Brandon Vigliarolo: 2.8%The Register: 1.2%Slippery Slope0.0%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.2%Circular Reasoning0.0%This article: 13.8%Brandon Vigliarolo: 9.4%The Register: 5.9%Hasty Generalization13.8%This article: 0.0%Brandon Vigliarolo: 0.3%The Register: 0.3%Red Herring0.0%This article: 0.0%Brandon Vigliarolo: 1.1%The Register: 0.7%Bandwagon0.0%This article: 10.3%Brandon Vigliarolo: 2.2%The Register: 3.0%Appeal to Emotion10.3%This article: 0.0%Brandon Vigliarolo: 2.1%The Register: 0.9%Begging the Question0.0%This article: 0.0%Brandon Vigliarolo: 2.3%The Register: 2.0%Post Hoc (False Cause)0.0%This article: 0.0%Brandon Vigliarolo: 0.1%The Register: 0.2%Tu Quoque0.0%This article: 1.3%Brandon Vigliarolo: 0.5%The Register: 0.7%Burden of Proof1.3%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.2%Appeal to Nature0.0%This article: 0.0%Brandon Vigliarolo: 0.5%The Register: 0.3%Composition/Division0.0%This article: 7.3%Brandon Vigliarolo: 2.1%The Register: 2.1%Anecdotal7.3%This article: 0.0%Brandon Vigliarolo: 0.1%The Register: 0.0%No True Scotsman0.0%This article: 13.6%Brandon Vigliarolo: 1.1%The Register: 2.1%Ambiguity (Equivocation)13.6%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.0%Gambler’s Fallacy0.0%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.1%Middle Ground0.0%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.1%Personal Incredulity0.0%This article: 0.0%Brandon Vigliarolo: 0.0%The Register: 0.2%Special Pleading0.0%This article: 0.0%Brandon Vigliarolo: 0.1%The Register: 0.2%Genetic Fallacy0.0%This article: 5.6%Brandon Vigliarolo: 1.1%The Register: 2.3%Unattributed Quote5.6%This article: 3.0%Brandon Vigliarolo: 0.8%The Register: 1.2%Quote-first Misdirection3.0%This article: 7.1%Brandon Vigliarolo: 2.6%The Register: 7.2%Biased Writer Voice7.1%This article: 0.0%Brandon Vigliarolo: 1.6%The Register: 1.5%Indoctrination0.0%This article: 0.0%Brandon Vigliarolo: 0.3%The Register: 0.1%Politically Left Leaning Bias0.0%This article: 0.0%Brandon Vigliarolo: 0.1%The Register: 0.1%Politically Right Leaning Bias0.0%This article: 24.7%Brandon Vigliarolo: 1.5%The Register: 2.6%Attempt to Sell a Product or S…24.7%

708 words analyzed.

Speakers

1speaker41%attributed speech415writer words
Voice mapSelect a segment to jump to its words
Writer's voice • 10 words • 100.0% coverageWriter's voice • 20 words • 0.0% coverageWriter's voice • 18 words • 100.0% coverageWriter's voice • 22 words • 0.0% coverageWriter's voice • 38 words • 0.0% coverageOmar Soutari • 19 words • 100.0% coverageOmar Soutari • 33 words • 0.0% coverageWriter's voice • 2 words • 100.0% coverageWriter's voice • 34 words • 100.0% coverageWriter's voice • 44 words • 0.0% coverageWriter's voice • 39 words • 0.0% coverageWriter's voice • 9 words • 0.0% coverageOmar Soutari • 21 words • 100.0% coverageWriter's voice • 24 words • 0.0% coverageOmar Soutari • 47 words • 0.0% coverageWriter's voice • 21 words • 0.0% coverageOmar Soutari • 31 words • 0.0% coverageOmar Soutari • 40 words • 100.0% coverageOmar Soutari • 37 words • 0.0% coverageOmar Soutari • 10 words • 0.0% coverageWriter's voice • 41 words • 100.0% coverageWriter's voice • 52 words • 0.0% coverageOmar Soutari • 32 words • 100.0% coverageWriter's voice • 24 words • 100.0% coverageOmar Soutari • 23 words • 0.0% coverageWriter's voice • 16 words • 100.0% coverageWriter's voice • 1 words • 0.0% coverage
Selected voice

Omar Soutari

100%flagged-word coverage
293 attributed words100% of attributed speech76% writer coverage
0%17.5%35.0%Attempt to Sell a Product -23.5 ptsWriter: 34.5%Omar Soutari: 10.9%10.9%Unattributed Quote+13.7 ptsWriter: 0.0%Omar Soutari: 13.7%13.7%Biased Writer Voice+11.2 ptsWriter: 2.4%Omar Soutari: 13.7%13.7%Quote-first Misdirection+6.0 ptsWriter: 0.5%Omar Soutari: 6.5%6.5%

Attribution is sentence-level. Pattern percentages are calculated only from words assigned to that voice.

Loading…
Loading…
Loading…
Loading…

Analysis

Hover over highlighted words in the article to view the associated bias or fallacy analysis.