Popular repositories Loading

1. eval-harness-evaluator-bbbarky-framework eval-harness-evaluator-bbbarky-framework Public

   Provider-agnostic evaluation framework for LLM agents: LLM-as-judge, pattern, and hybrid evaluators with a YAML runner, Wilson-CI reporting, and CLI.

   Python 1

2. hermes-ai-software-team-pipeline hermes-ai-software-team-pipeline Public

   Python CLI that turns a product idea into a Hermes Kanban role graph — full-SDLC pipeline with PM → UX → Architect → Dev → Review → QA → Release

   Python 1

3. AssesmentApril AssesmentApril Public

   iOS app to search and filter countries by name or capital in real time, built with UIKit and an MVVM architecture in Swift.

   Swift

4. playwright-kanban-assessment playwright-kanban-assessment Public

   Data-driven Playwright + TypeScript E2E test suite for a demo Kanban board, using the Page Object Model, fixtures, and JSON-driven test data (one test generated per scenario).

   TypeScript

5. QA_Assistant_Playwright QA_Assistant_Playwright Public

   Local-first AI workbench that turns prompts, Jira tickets, and DOM snippets into test plans, locators, and Playwright/Selenium/Cypress skeletons. FastAPI backend, React frontend, multi-LLM.

   Python

6. invoice-extraction-pipeline invoice-extraction-pipeline Public

   Evidence-centered document extraction pipeline with LLM extraction, validation routing, and human review UI

   Python