A review of the gbrain knowledge-brain deployment, how it's being used, how to wire it into your AI tools, and how (and whether) it ingests email, CRM, and NetSuite.
Since this review the gaps below were fixed and verified live in the brain:
mcp-remote; the stale Codex→Hermes MCP entries were repointed from the decommissioned Hostinger host to vps2 (handshake verified)./query now hits gbrain semantic search first; /ingest now enforces commit + push so authored pages actually reach the brain./mcp → gbrain → authenticate browser step./query, /ingest, and /lint read raw markdown files from the Obsidian vault — they never called the brain's semantic search. (Fixed — see update.)Net effect at review time: you'd built a brain, then kept reading the filing cabinet. The retrieval-quality win (hybrid keyword + vector + knowledge-graph) was sitting unused on your interactive tools. None of it was broken architecture — and most of it is now fixed.
gbrain v0.41.26.0 runs in Docker on vps2 (Hetzner) as gbrain-http + gbrain-postgres (pgvector), fronted by brain.huxapps.com through a Cloudflare Tunnel. The /admin path sits behind Cloudflare Access + Google SSO; /mcp behind OAuth 2.1. Its internal enrichment LLM runs through a loopback Codex bridge (your ChatGPT subscription), so marginal cost is roughly $1–5/month (embeddings only).
The wikis are the system of record; gbrain is a search projection, never the source of truth. Everything flows wikis → git → brain, never the reverse. Keep this in mind for every recommendation below.
Total page count is 843 — that includes 362 pages in the inert legacy default corpus (pre-v0.17, never synced, harmless). The 481 figure is the real, searchable wiki content across 9 sources (up from 413 at review time, after the suppliers fix).
| Source | Pages | Last sync | |
|---|---|---|---|
| products | 197 | 2026-06-01 | |
| company-context | 95 | 2026-05-29 | |
| suppliers | 71 | 2026-06-01 | fixed — was 6 |
| vps-architecture | 41 | 2026-06-01 | |
| odoo-implementation | 22 | 2026-05-28 | |
| systems-handbook | 19 | 2026-06-01 | conflict resolved |
| lead-gen | 17 | 2026-05-28 | |
| training | 10 | 2026-05-28 | |
| assets | 9 | 2026-05-28 | |
| default (legacy) | 362 | never | inert |
materials/, vendors/, intelligence/) authored locally but never pushed to GitHub. Committed, pushed, re-synced → 71 in the brain.git stash pop conflict in index.md — resolved (kept all three additive rows) + processes.md added.gbrain serve pattern is obsolete on the v0.41 thin-client) — rewired to mcp-remote.Claude Code (Mac) still needs the one-time /mcp → gbrain → authenticate browser step. The hourly wikis-sync → gbrain-sync timers are confirmed healthy — the gaps above were all authoring-side (unpushed edits), not sync failures.
The brain was installed 2026-05-28 — days before this review, so there's no 30-day history. In its first few days:
Two layers: fix the plumbing, then retarget the skills. Both were actioned this session.
npx -y mcp-remote https://brain.huxapps.com/mcp (handles OAuth, caches the token). First run opens a browser for consent./mcp → gbrain → authenticate once (browser).wiki-query now calls mcp__gbrain__query with source_id:"__all__" (cross-wiki — gbrain does not federate by default) first, files only as fallback. wiki-ingest now ends with a mandatory commit + push step — the exact gap that left 64 suppliers pages invisible to the brain.
Today, the brain's only live intake is the wiki Git repos, pulled hourly and synced into Postgres. Nothing else flows in automatically.
Your Hermes agents (huxberrypm Gmail intake, Meet ingestion, scrapers, assetops) write markdown into a wiki's raw/inbox/, which becomes brain content on the next sync. So email and meeting data reach the brain only if a Hermes job or you ingest it into a wiki first. This keeps the "wikis = source of truth" principle intact.
| Sense | Source | Status |
|---|---|---|
| email-to-brain | Gmail (via ClawVisor gateway or Google OAuth) | available · not set up |
| calendar-to-brain | Google Calendar | available · not set up |
| meeting-sync | Circleback transcripts | available · not set up |
| x-to-brain | Twitter / X | available · not set up |
| NetSuite / Odoo (CRM) | — | no native sense exists |
company-context/wiki/crm-pipeline.md — open deals by stage/owner, top accounts, refreshed daily) → push → brain. Don't dump raw records.odoo-to-brain): a markdown recipe + collector, validated with gbrain integrations test. More moving parts — revisit only if curated summaries fall short.NetSuite is lower priority since it's migrating to Odoo. The native email/calendar/meeting senses are an alternative for raw intake, but they bypass wiki review — only worth it if you specifically want a searchable firehose.
mcp-remote; Hermes MCP entries repointed to vps2. (Claude Code browser auth remains your one manual step.)/query uses gbrain first; /ingest enforces commit + push.