Claude Second Brain Harness

Ship #1 Pending review

@xerneas on Claude Second Brain Harness · 19 days ago

Claude Harness that is light enough and not extra enough for daily use. After messing around with openclaw I saw that the costs and features were simply too extra. This is a great life planner that can be run simply even with lower end models like claude haiku.

1 devlog
1h

Try project → See source code →

Open comments for this post

@xerneas on Claude Second Brain Harness · 19 days ago

58m 46s logged

What it is
A markdown-only second-brain that Claude Code reads at every session start and edits as you talk to it. Everything lives as plain .md files in a fixed directory tree- no database, no proprietary format.

Two repos, one system

brain-template: the harness itself. CLAUDE.md (the session-start instructions Claude reads), a templates/ folder, and a directory skeleton (daily/, backlog/, goals/, notes/, projects/, routines/, memory/, archive/). Drop your real notes in, edit memory/context.md, and Claude becomes a proactive planner.
ClaudePlanner: the phone + sync layer on top of the harness. iOS app (SwiftUI) for Today/Browse views with tap-to-toggle, drag reorder, talk-to-Claude with on-device speech. A Node sync-daemon does bidirectional brain/ ↔ Firestore sync. A Fastify relay exposes the Claude Agent SDK with Firebase auth + MCP tools (list_today, read_file, add_task, check_task).

Flow

You write/edit a task in daily/today.md (or tell Claude on phone, or check a box).
sync-daemon mirrors the change to Firestore.
iOS app live-listens and updates instantly.
Closing the loop: when Claude (on phone or terminal) edits files via the relay, sync-daemon writes them back to disk.

Full iOS and server support will be shown soon