Agentic interface for mainframes and COBOL
Hi HN, we’re Sai and Aayush, and we’re building Hypercubic (https://www.hypercubic.ai/), bringing AI tools to the mainframe and COBOL world. (We did a Launch HN last year: https://news.ycombinator.com/item?id=45877517.) Today we’re launching Hopper, an agentic development environment for mainframes. You can download it here: https://www.hypercubic.ai/hopper, and you can also request access and immediately get a mainframe user account to play with. There's also a video runthrough at https://www.youtube.com/watch?v=q81L5DcfBvE. Mainframes still run a surprising amount of critical infrastructure: banking, payments, insurance, airlines, government programs, logistics, and core operations at large institutions. Many of these systems are decades old, but they continue to process enormous transaction volumes because they are reliable, secure, and deeply embedded into business operations. A lot of that software is written in COBOL and runs on IBM z/OS. The development environment looks very different from modern cloud or Unix-style development. Instead of GitHub, shell commands, package managers, and CI pipelines, developers often work through TN3270 terminal sessions, ISPF panels, partitioned datasets, JCL, JES queues, spool output, return codes, VSAM files, CICS transactions, and shop-specific conventions. TN3270 is the terminal interface used to interact with many IBM mainframe systems. ISPF is the menu and panel system developers use inside that terminal to browse datasets, edit source, submit jobs, and inspect output. It is powerful and reliable, but it was designed for expert humans navigating screens, function keys, and fixed-width workflows, not AI agents. A simple COBOL change might require finding the right source member, checking copybooks, locating compile JCL, submitting a job, reading JES/SYSPRINT output, interpreting condition codes, patching fixed-width source, and resubmitting. Much of this work is so well-defined and repetitive that it's a good fit for agentic AI. To get that working, however, a chatbot next to a terminal is not enough. The agent needs to operate inside the mainframe environment. Hopper combines three things: (1) A real TN3270 terminal, (2) Mainframe-aware panels for datasets, members, jobs, and spool output, and (3) An AI agent that can operate across those z/OS surfaces. For example, here is a tiny version of the kind of thing Hopper can help debug: COBOL: IDENTIFICATION DIVISION. PROGRAM-ID. PAYCALC. DATA DIVISION. WORKING-STORAGE SECTION. 01 CUSTOMER-BALANCE PIC 9(7)V99. PROCEDURE DIVISION. ADD 100.00 TO CUSTOMER-BALNCE DISPLAY "UPDATED BALANCE: " CUSTOMER-BALANCE STOP RUN. JCL: //PAYCOMP JOB (ACCT),'COMPILE',CLASS=A,MSGCLASS=X //COBOL EXEC IGYWCL [//COBOL.SYSIN](https://cobol.sysin/) DD DSN=USER1.APP.COBOL(PAYCALC),DISP=SHR [//LKED.SYSLMOD](https://lked.syslmod/) DD DSN=USER1.APP.LOAD(PAYCALC),DISP=SHR A human would submit this job, inspect JES output, open `SYSPRINT`, find the undefined `CUSTOMER-BALNCE`, map it back to the source, patch the member, and resubmit. Hopper is designed to let an agent operate through that same loop autonomously. Hopper is not trying to hide the mainframe behind a generic abstraction, and it's not a chatbot. The design principle is simple: preserve the fidelity of the mainframe environment, but make it accessible to AI agents. Sensitive operations require approval, and the terminal remains visible at all times. Once agents can operate inside the mainframe environment, new workflows become possible: faster job debugging, automated documentation, safer code changes, test generation, migration planning, traffic replay, and modernization verification. We’re curious to hear your thoughts! especially from anyone who has worked with mainframes, COBOL or has done legacy enterprise modernization.
Open-source 2D IDE for managing agent CLIs
Show HN: Open-source 2D IDE for managing agent CLIs
CADara
Show HN: CADara – I made an open-source in-browser CAD
I built an open-source, local-first alternative to LangSmith
Hey HN. Built this because LangSmith needs a cloud account just to see my own traces. pip install opensmith — everything shows up at localhost:7823. SQLite. No accounts. No config. Fully offline. 800+ downloads in 2 days. Surprised me. Would love honest feedback from this community.
Crit
Crit is a single-binary CLI that opens your file or code diffs in a browser with GitHub-inspired interface. Your favourite agent acts on the feedback and responds back - continue until you're happy. I've been building this for a few months now and it's been helping me a lot juggling parallel conversations with agents, making it easier to actually review the plans they generate and the resulting code - all before it hits GitHub. It also allows you to export the plans to a hosted service (which you can self-host for privacy), to solicit feedback from your team. No account needed, and reviews are automatically deleted after 30 days of inactivity.
I built an open-source email builder, alternative to Beefree/Unlayer
Show HN: I built an open-source email builder, alternative to Beefree/Unlayer
Red Squares
Show HN: Red Squares – GitHub outages as contributions
Open-source CLI to generate UI tests from user flows
Show HN: Open-source CLI to generate UI tests from user flows
Bonsai 1.7B ternary model at 442T/s on M4 Max
We took a recently released Bonsai 1.7B ternary model from PrismML (https://github.com/PrismML-Eng/Bonsai-demo) and ran our agentic evolution search on it for 6 hours to optimize the Metal kernels. The search was fully autonomous. Measured against unmodified upstream llama.cpp at the same Bonsai/Q2_0 commit, same M4 Max: - tg128: 309.82 → 442.42 t/s (+42.0%) - pp512: 4250.32 → 4622.63 t/s (+8.8%)
Generate SKILL.md files from URLs, in the browser
I created this tool after writing a few agent skills by hand and noticing this pattern was repetitive. Paste a documentation URL, enter your own model API key, and it gets the page content client-side to create a reusable SKILL.md. There is no backend/proxy, so it stays as secure as possible. I would like feedback on the structure of the output and the edge cases.
State of the Art of Coding Models, According to Hacker News Commenters
Hello HN, I was away from my computer for two weeks, and after coming back and reading the latest discussions on HN about coding assistants (models, harnesses), I felt very out of the loop. My normal process would have been to keep reading and figure out the latest and greatest from people's comments, but I wanted to try and automate this process. Basically the goal is to get a quick overview over which coding models are popular on HN. A next iteration could also scan for harnesses that people use, or info on self-hosting or hardware setups. I wrote a short intro on the page about the pipeline that collects and analyzes the data, but feel free to ask for more details or check the Google Sheet for more info. https://hnup.date/hn-sota
Large Scale Article Extract of Newspapers 1730s-1960s
Hello HN, over the past 7 months I've spent nearly 3,000 hours on building SNEWPAPERS, the first historical newpaper archive with full-text extractions, nearly perfect OCR, a vast categorization taxonomy and of course with semantic and agentic search capabilities. Problem: I wanted to search through newspaper archives, but when I tried every service only lets you search for keywords and dates, and gives you back raw images of the papers, and too many of them with no context. A sea of noise. Solution: I taught machines how to read the newspapers and so far I've extracted the content from > 600k pages (about 5TB) from the Chronicling America collection. Problems I had to deal with were an infinite variety of layouts, font sizes, image scan qualities, resolutions, aspect ratios, navigating around the images on the page. I also had to figure out how to get OCR to be nearly perfect so people wouldn't hate reading the extracts. I stitched together a multi-model pipeline (layout tech, ocr tech, llm, vllm) with heuristics to go from layout -> segmentation -> classification. I put it all in OpenSearch / Postgres and made it semantically searchable and also put an agentic search tool on top that knows how to use the API really well and helps you write queries to find what you're looking for. Happy to discuss AWS architecture and scaling as well, that was tough! If you have five minutes and you just want to jump in and have your own personalized experience, what I would suggest is: Before searching for anything, go to the Sleuth page Ask it about anything from 1736 to 1963, maybe 1 or 2 follow up questions Then go to the search page so you can see the queries it wrote for you (bottom left "saved queries") and uncover more info on whatever it is you're interested in If you think it's cool and you want to learn more, then there's about 10 minutes of video guides on the various capabilities in "Guide" on the nav bar Some other people have also taken a crack at this, notably: https://dell-research-harvard.github.io/resources/americanst... (very good attempt) https://labs.loc.gov/work/experiments/newspaper-navigator/ (focused on images)