Enables multi-agent code review with P0/P1/P2 severity scoring by orchestrating locally installed AI CLIs (Claude, Codex) to perform parallel analysis, deterministic scoring, and consensus-building on git diffs.
AI-powered code review server that analyzes git diffs and PRs with context from project guidelines and task lists. Supports integration with Claude Code and Cursor via MCP.
Enables auditable, plan-linked Git commit review views for Codex, with interactive file trees, split diffs, line-level explanations, and SHA-256 audit receipts served locally on localhost.