Agentic Workforce Company
Agent Infrastructure · Flagship

A second brain my AI agents actually read.

The Agentic Brain is a git-backed Markdown vault — the shared long-term memory for me and my agents. Obsidian for humans, GitHub as the source of truth, synced across a MacBook and three Mac minis, with real write-governance and a compiling knowledge wiki so agents don’t corrupt it.

Live & in daily useYoung · iteratedROLE Architect & OwnerSINCE Jun 2026
CategoryAgent infrastructure
Source of truthholisticseo/agentic-brain (private)
NodesMacBook bridge · 3 Mac minis · GitHub
TimeframeJun 2026 → ongoing
StatusLive · actively built
The Problem

Models change. Tools change. The knowledge shouldn't.

Every agent started cold.

My agents were trapped in their own runtime memory — no shared, durable, verified knowledge base to draw on.

Each model I wanted to use — the OpenClaw agents, Hermes, Claude Code, Claude Co-Work, Codex — re-derived, re-verified, and re-lost the same facts in every tool. Months of career proof, client SOPs, business strategy, and research were piling up with no system to turn raw material into linked, reusable knowledge.

And a governance problem was waiting to happen: the moment agents could write to the source of truth, one sloppy edit could quietly corrupt it — and I’d trust it anyway, because it looked clean. I wanted one canonical brain every model could read, that I could edit like notes, that survived any single tool going away, and that had rules to keep a writable brain from rotting.

The Approach

Four layers on one idea: the folder is the asset.

The real asset is the plain-Markdown folder, not the app. From there the system has four layers, each with a clear job.

File over app. File over AI. If Obsidian, Claude, or Codex disappear tomorrow, the brain is still mine — still readable, still complete.

— Founding principle of the vault
Layer 01 · Interfaces

Obsidian for humans, Git for agents.

Obsidian gives me linked notes, backlinks, graph view, and a Web Clipper for intake. GitHub is the durable source of truth for agents — universal, inspectable, versioned, and not dependent on Obsidian being open. Every machine holds a local clone; agents pull before they read or write.

Layer 02 · Architecture

Numbered domains, one front door.

Nine numbered top-level folders so humans and agents always know where a thing lives and who owns it. A root START.md is the front door every agent reads first; me.md is the canonical durable profile that runtime files defer to instead of duplicating.

Layer 03 · Governance

A writable brain needs contracts.

A protected core only the lead agent or I edit directly; declared folder ownership; and four contribution states — canonical, draft, proposal, archive. Nothing is treated as truth until I approve it. The operating rule for agents: brain first.

Layer 04 · LLM Wiki

Raw intake that compiles into knowledge.

An immutable raw/ intake folder, a fingerprinted source registry, and a compiled wiki/ layer where an agent extracts entities, concepts, syntheses, and open questions into interlinked pages. It compiles knowledge instead of just retrieving files, so the brain compounds over time.

Architecture & Sync

Sync topology.

GitHub is the source of truth at the center. The MacBook Pro bridges Obsidian to Git in auto mode; the three agent minis run as pull-only clones so in-progress agent work is never auto-committed. An installed launchd job keeps all four in sync on a five-minute cadence.

Fig.01 — Agentic Brain Sync TopologyAgentic Brain sync topology across five nodesOn the human side at the left, Obsidian feeds a MacBook Pro that acts as the bridge. The MacBook syncs bidirectionally with a central GitHub repository, holisticseo/agentic-brain on branch main, which is the source of truth. This MacBook-to-GitHub link runs in auto mode: commit, rebase, push, guarded by a Gitleaks secret scan. On the right, three Mac minis run the agent fleet — MC and Hermes, Claude Code and Codex, and Claude Co-Work — each cloning from GitHub in pull-only mode. An installed launchd job named com dot agenticbrain dot sync fires every five minutes across all machines, and conflicts stop for manual review rather than being auto-resolved.HUMAN SIDEObsidianhuman interface · Web ClipperBRIDGE · AUTO MODEMacBook Procommit · rebase · pushedits landSOURCE OF TRUTHGitHubprivate repoholisticseo/agentic-brainbranch: main1 canonical source · 5 nodesAUTO · 2-WAYgitleaks secret-scan gateAGENT MINIS · PULL-ONLYMac mini 01MC · Hermespull-only cloneMac mini 02Claude Code · Codexpull-only cloneMac mini 03Claude Co-Workpull-only clonePULL-ONLYlaunchd · every 5 mincom.agenticbrain.sync⚠ conflicts stop for manual review · never force-push · never auto-pick a side

Obsidian edits land on the MacBook Pro bridge, which commits, rebases, and pushes to GitHub — the one canonical source of truth (holisticseo/agentic-brain, main). The three Mac minis pull that repo in pull-only mode so agent work-in-progress is never auto-committed. An installed launchd job runs every five minutes on all four machines. A Gitleaks scan gates every sync, and conflicts stop for manual review rather than being silently resolved.

Vault & Format

plain Markdownrelative-link standardnumbered domainsSTART.md front door

Source & Interface

GitHub (private)gitObsidianWeb Clipper

Sync Automation

launchdbrain-sync.shlock-based concurrencyauto / pull-only5-min cadence

Safety & Secrets

Gitleaksbrain-secret-scan.shhistory-epoch guardconflict-stops

Governance

protected corefolder ownershipcanonical/draft/proposal/archivebrain-first rule

LLM Wiki Layer

immutable raw/wiki-register-source.shSHA-256 fingerprintwiki-lint.sh
By the Numbers

One brain, replicated.

Structural counts verified from the live vault on the MacBook clone and the build thread.

Sync nodes
5
MacBook bridge + 3 Mac minis + GitHub cloud
Knowledge domains
9
numbered top-level folders + raw/ & wiki/
Governance docs
20
write-governance, doctrine, sync model, QC records
Agent runtimes
5
MC, Hermes, Claude Code, Claude Co-Work, Codex
6
shell scripts running the machinery — 3 sync, 1 secret scanner, 2 wiki
4
launchd sync jobs on a 5-min cadence — 1 auto (MacBook), 3 pull-only (minis)
~51
compiled wiki pages from the first ingest batch, all interlinked
~289
Markdown files in the vault (~467 total files) and growing
4
contribution states gating what agents treat as truth, over a protected core
1
canonical source of truth — the private GitHub repo on branch main

The first LLM Wiki ingest compiled 24 registered sources into 9 entities, 11 concepts, 3 syntheses, and 4 open-question notes — roughly 51 interlinked pages, lint-passing for orphans and broken links. Every phase closed with a written QC record inside the vault.

The Governance Model

A writable brain needs contracts.

A shared, agent-writable brain without rules becomes an unreviewed dump. So on top of the files sits a governance layer: a protected core, declared ownership, and four explicit states that gate what counts as truth.

Protected core

The root instruction files — START.md, me.md, vault-map.md, skill-map.md, CLAUDE.md, the history-epoch marker — and all of 00-system/ are edited directly only by the lead agent (MC) or by me. Every other agent proposes changes. Each numbered domain has a declared owner and a “Mike-owned, agent-assisted” rule set.

State 01

Canonical

Approved truth. Nothing reaches this state until I promote it. Agents read it as authoritative.

State 02

Draft

In progress. Strategy, offers, and pricing stay here until reviewed — never treated as fact.

State 03

Proposal

Agent-authored change awaiting my sign-off. Client-facing claims and positioning live here first.

State 04

Archive

Superseded or parked material kept for traceability — out of the way, still versioned.

Brain first: check the vault before searching the outside web or reinventing context.

— Agent operating doctrine
The LLM Wiki Layer

Raw intake that compiles into knowledge.

Adapted from Andrej Karpathy’s LLM Wiki pattern: three tiers that turn a raw drop into linked, reusable knowledge instead of a dead pile of files — so the brain compounds over time.

Tier 01

Raw drop

Anything — Markdown, PDFs, images, transcripts, web clips — lands in an immutable raw/ folder. Never edited.

Tier 02

Registered source

A source registry fingerprints each source with a SHA-256 hash via wiki-register-source.sh.

Tier 03

Compiled

An agent extracts entities, concepts, syntheses, and open questions into a wiki/ graph.

Output

Linked wiki page

Interlinked Markdown, health-checked by wiki-lint.sh for orphans, broken links, and low-confidence claims.

Neutral worked example: “How Search Engines Work” — raw source through to a compiled, lint-passing wiki page.

What's Real

What exists — and an honest status.

Two separate ledgers. The left is what is built, running, and verified in the live vault. The right is the honest status — kept deliberately distinct so proven facts never blur into roadmap.

● Built, running & verified

A live, governed, git-backed second brain in daily use.

  • One canonical GitHub source of truth, editable in Obsidian, read by all five agent runtimes.
  • Kept in sync across four machines by an installed launchd automation — auto on the bridge, pull-only on the minis.
  • Every sync is secret-scanned with Gitleaks; conflicts stop for review instead of corrupting truth.
  • Governance assigns ownership and gates canonical promotion behind my approval.
  • Populated and in use: career profile, a source-backed claim library, client folders, business context.
  • A working LLM Wiki took its first source from a raw drop through to compiled, linked, lint-passing pages.
⚠ Honest status · not a finished platform

Young, actively-iterated infrastructure — not a mature product.

  • Started June 2026: Phase 1 scaffold → GitHub sync → LLM Wiki → automated multi-machine sync → a supervised history rewrite.
  • The LLM Wiki is still supervised manual ingest (Phase 1): I drop files, then prompt an agent to register and compile them.
  • Automatic watching, extraction, and auto-compiling are planned later phases, not shipped.
  • Garry Tan’s GBrain was evaluated and deliberately deferred — the file-native version ships first and stays canonical.

Framed correctly: living infrastructure I designed and operate, under active buildout — not a fully-autonomous, self-compiling, battle-tested platform.

Build Timeline

From scaffold to running fleet.

2026-06-22 · Phase 1
Scaffold QC'd and approved

MC scaffolded the numbered folders and seeded me.md and the vault map. Claude pressure-tested it — approved after fixes: misfiled notes moved, an unplanned folder removed, secret-ignore rules hardened.

2026-06-22 · Sync
GitHub sync across all four machines

The private repo became the source of truth; every machine took a local clone. Relative links pass, no stray wikilinks, main matching the clones.

2026-06-27 · Wiki
LLM Wiki Phase 1

First real source taken from a raw drop through registration and compilation to linked, lint-passing wiki pages.

Ongoing · Automation
Installed multi-machine sync

A hardened brain-sync.sh plus a launchd installer — com.agenticbrain.sync — on a 5-minute cadence: auto on the bridge, pull-only on the minis.

2026-07-14 · Guarded
Supervised history rewrite

A history-epoch marker guards against replaying purged commits after an intentional rewrite — sync refuses to rebase across a mismatch.

My Role

I owned the architecture and the hard calls.

I owned the vision and the hard decisions: file-over-app, GitHub-as-truth over Obsidian Sync for agents, the numbered-domain structure, the protected core, and the canonical/draft/proposal/archive discipline.

I made the call to adopt the Karpathy LLM Wiki now while deferring GBrain. I directed MC — my primary OpenClaw agent and the declared owner of 00-system — to build the scaffold, seed the profile and vault map, stand up the sync scripts and launchd automation, and run the wiki ingests, then reviewed and approved as it went, with Claude pressure-testing before sign-off. I set the guardrails: business strategy, client claims, and positioning stay draft until I promote them; secrets and unsanitized exports never enter git. I am the owner and final decision-maker; the agents are the builders I direct.

Skills Demonstrated

What this took.

Knowledge-management architectureFile-over-app / local-first designGit-based multi-machine sync designlaunchd automationLock-based concurrencyConflict-stop safety designData governance & access controlSecret-hygiene engineering (Gitleaks)History-epoch guardingAI agent context engineeringMulti-agent knowledge sharingInformation architectureLLM Wiki / compiling knowledge baseObsidian + Markdown systemsTechnical direction & QC of AI agents

Want an operator who builds the memory layer — not just prompts?