@featured
See what your coding agent actually did. A desktop pal and notch for Claude Code, Codex, Cursor, Gemini CLI and any agent: test results read from the output, faked passes caught, Claude Code sent back to fix what it broke, and an MCP server any AI tool can ask.
@featured
Local MCP for Chief of Staff agents to run Codex and Claude Code CLI project sessions with scoped access and durable receipts.
@featured
MCP review board that lets different coding agents review each other — object → revise → pass, append-only audit trail. For Claude Code, Codex, OpenCode, Trae, ZCode.
@featured
Terminal-native DOM perception layer for AppSec and AI. Hook into live Chrome sessions, compress HTML tokens by 98.9%, and map attack surfaces deterministically.