Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
-
Updated
May 7, 2026 - Shell
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
Chrome-first shopping extension product family with 8 storefront apps, 1 Suite shell, a reviewer-facing release shelf, and a read-only stdio MCP surface.
Archived TaijiOS legacy prototype; current main repo is yangfei222666-9/taiji.
Tool-agnostic engineering workflow plugin for AI coding agents. Surface-first change analysis, source-of-truth discipline, Lean/Full modes, phase-gate discipline, evidence-driven delivery. Works with Claude Code, Cursor, Gemini CLI, Windsurf, Codex, Aider, OpenCode.
Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply
EDPA — Evidence-Driven Proportional Allocation. Derive hours from Git evidence. No timesheets.
Add a description, image, and links to the evidence-driven topic page so that developers can more easily learn about it.
To associate your repository with the evidence-driven topic, visit your repo's landing page and select "manage topics."