🤓 Latest Submissions
Countersign: No Evidence, No Pass
Countersign is a pre-commit gate for projects where AI agents write most of the code. One human-owned file, countersign.yaml, turns each requirement into a shell check: bandit, detect-secrets, pytest, ruff, and source-level rules like "the DELETE route must still exist". A requirement with no check is UNVERIFIED, never PASS. Any security failure or unverifiable security check blocks the commit, any functional failure blocks it, and quality issues only warn. Every run writes a hash-chained evidence record. watsonx.ai (Granite) reads the failures and explains them in plain language, but the verdict is fixed before the model is called, and a guard withholds any explanation that contradicts the result. Then the record goes to IBM Z through Zowe, where a JCL job re-verifies the exact bytes on USS. CC 0000 approves it and appends it to a ledger on Z; CC 2048 or no answer blocks the commit. z-audit later catches any approved record that was edited. The same rules file drives the hook, a read-only GitHub Action, and IBM Bob's own rules. It installs with one pip command and a python -m countersign init on any existing repo, and a Streamlit dashboard shows every run, its evidence, and the stored watsonx explanation.
27 Sep 2026
Rosetta — AI Database Onboarding Tool
New developers joining a team often inherit databases with dozens or hundreds of tables and no documentation. Understanding the schema, key relationships, and how to write useful queries can take days or weeks of painful reverse-engineering. Rosetta solves this by automating the entire onboarding experience. You connect it to a SQL Server or SQLite database, and within minutes it produces a complete, interactive documentation hub tailored to that database. Under the hood, Rosetta uses pyodbc and sqlite3 to inspect the live schema — extracting tables, columns, data types, foreign key relationships, and row counts directly from the database system catalog. That metadata is then sent to the Groq API running Llama 3.1 8B Instant, which generates a plain-language database overview, one-sentence descriptions for every table, a ranked list of the five most important tables to learn first, and a set of starter SQL queries a new developer would actually need. The result is a 7-page Streamlit application with: a natural language overview of what the database is and what it stores, an interactive force-directed schema map showing every table and foreign key relationship color-coded by schema, a "Spotlight" guide ranking which five tables matter most and why, a library of AI-generated queries you can run live and download as CSV, a searchable and filterable table glossary with full column details, and a one-click PDF export of the complete onboarding document. A built-in SQLite demo database with 37 tables is included so anyone can try the full experience without a database connection. Built entirely in Python using Streamlit, pyodbc, pandas, streamlit-agraph, reportlab, and the Groq API — Rosetta deploys for free on Streamlit Cloud.
17 May 2026
