What problem does it solve? Setting up a persistent memory and search backend for a coding agent involves many manual steps: installing the gbrain CLI, choosing a storage engine, registering an MCP server, and defining per-repo trust policies. This Skill compresses that into one guided, idempotent workflow. ## Core Features & Use Cases - End-to-end gbrain setup: Installs the CLI, initializes a local PGLite or Supabase brain, and registers the MCP server (local stdio or remote HTTP with bearer token verification). - Transcript and memory ingest: Optionally ingests Claude Code, Codex, and Cursor session transcripts plus learnings, timelines, and design docs into gbrain, with optional gitleaks secret scanning. - Trust policy and artifacts sync: Captures per-remote trust policy (read/write/deny) and configures cross-machine artifact sync to a private GitHub or GitLab repo. - Use Case: A developer on a new machine runs the setup once and gets a working semantic search brain over their code and past sessions, with remote-MCP mode for connecting to a teammate's hosted gbrain server. ## Quick Start Ask the agent to set up gbrain on this machine and connect it to this project.