What problem does it solve? Setting up a persistent memory and knowledge backend for a coding agent involves many manual steps: installing the gbrain CLI, choosing a storage engine, registering an MCP server, and defining trust policies per repository. This Skill automates that entire bootstrap flow in one guided command. ## Core Features & Use Cases - End-to-end gbrain installation: Installs the gbrain CLI, initializes a local PGLite database or connects to Supabase, and registers the MCP server with the coding agent host. - Remote MCP mode (Path 4): Connects to a remote gbrain server over HTTP with a bearer token, verifying connectivity and classifying failures as NETWORK, AUTH, or MALFORMED with remediation hints. - Per-repo trust policy and transcript ingest: Captures read/write/deny trust policies per git remote and optionally ingests Claude Code and Codex session transcripts, learnings, and design docs into gbrain with optional gitleaks secret scanning. - Use Case: A developer on a new machine runs the setup once and gets a working semantic memory layer, so later sessions can query past conversations and project artifacts with gbrain search instead of cold-starting. ## Quick Start Ask the agent to set up gbrain on this machine, for example by saying "set up gbrain and connect it to this project".
