claude-chief-of-staff

KO | EN

gitlite — search

#typescript #ai-agents #ai #dsh-plugin #deepseek-harness #open-source #claude-code #codex #cli #developer-tools #react #windows

claude-chief-of-staff

★ 65 Open GitHub ↗

How I turned Claude Code into a persistent AI chief of staff — the full architecture, now installable as a plugin in one command.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Claude Code Chief of Staff

How I turned Claude Code into a persistent AI chief of staff — the full architecture, from CLAUDE.md to scheduled background scripts.

Built with Claude Code by [@loganinthefuture](https://www.tiktok.com/@loganinthefuture)

---

## Install it as a plugin (new)

The architecture below is now installable in one command. In Claude Code:

```
/plugin marketplace add loganhc-09/claude-chief-of-staff
/plugin install chief-of-staff@chief-of-staff
```

Restart Claude Code, then run `/chief-of-staff:setup` — it interviews you and scaffolds your own persistent memory + daily-brief system. No coding required. The plugin lives in [`plugins/chief-of-staff/`](plugins/chief-of-staff/); everything it creates is plain Markdown on your machine.

---

## The Three Layers

The system has three layers. Most people are already at Layers 1 and 2. The unlock is Layer 3.

**Layer 1 — Knowledge (Vault):** A markdown vault Claude Code reads and writes. Start with the [`examples/CLAUDE.md`](examples/CLAUDE.md) template. That's the smallest viable version of this entire system — works the moment you drop it in a folder you `claude` from.

**Layer 2 — Active (MacBook + Claude Code):** You + Claude Code in the moment. Live work, live decisions. Already running if you have Claude Code installed.

**Layer 3 — Autonomous (always-on machine):** A second machine running scheduled scripts that pull email, calendar, transcripts, and post to Discord. Mine is an old laptop on my desk. Could be a Raspberry Pi, a Mac mini, or a cheap cloud VM. See [`architecture.md`](architecture.md) and [`examples/scripts/`](examples/scripts/) for what runs there.

**Cost:** I run on Claude Max ($200/month). Most of this works on Max 5x ($100/month) too — see [getting-started.md](getting-started.md#before-you-start-picking-your-plan-and-keeping-costs-down) for plan-tier breakdown and cost-reduction habits.

---

## What This Is

Most people use Claude Code for one-shot tasks. Write this email. Fix this bug. Explain this code. That's useful — but it's like hiring a brilliant contractor and only giving them 15-minute jobs.

This repo is the architecture for something different: a **persistent operational layer** that remembers your context, runs in the background, and compounds over time. Morning briefings generated before you wake up. Meeting transcripts processed into facts and follow-ups overnight. Commitments tracked and surfaced when they're overdue.

It's the difference between "I use AI sometimes" and "AI is part of how I operate."

## Architecture Overview

```
DATA SOURCES
  Calendar · Email · Meeting Transcripts · Analytics · Notes
  Discord conversations · YouTube channels · Newsletters · RSS feeds
                          ↓
SCHEDULING LAYER
  launchd/cron jobs · Session hooks · Reminder scripts
  Discord bot (always-on) · Content scout (daily)
                          ↓
PROCESSING
  Transcript extraction · Email triage · Briefing generation
  Follow-up tracking · Content pipeline · Data analysis
  Reading curation · Signal extraction · Cross-source clustering
  Discord fact mining · Approval gate routing
                          ↓
KNOWLEDGE STORE
  SQLite memory (facts, knowledge profile, milestones)
  Semantic search (QMD) · Follow-up queue · Decision log
  Meeting archive · Position documents · Network map
  Reading preferences · Source trust scores · POV pillars
                          ↓
OUTPUTS
  Morning briefings · Draft messages · Reminders
  Content drafts · Intelligence briefs · Approval queues
  Discord channels · Reading recommendations
```

See **[architecture.md](architecture.md)** for the full system diagram, data flows, memory layout, and scheduling config.

## The Handoff Model

The key design decision: not everything needs human involvement at every step. Three modes of work, explicit about where AI hands off to you.

**Automated:** Process transcripts, sync data, generate briefings, flag overdue items. AI owns it.

**Approval-gated:** Draft replies for you to review. Triage inbox for you to prioritize. Surface follow-ups for you to act on. AI preps, you decide.

**Human only:** Send messages, publish content, make judgment calls, strategic decisions. Never automated.

Most AI setups try to do everything or nothing. This one is explicit about where the handoff happens.

## What's In Here

### Core Architecture
| File | What It Is |
|------|-----------|
| [architecture.md](architecture.md) | Full system diagram, data flows, memory layout, scheduling |
| [getting-started.md](getting-started.md) | Progressive build guide — Day 1 to Month 3+ |
| [examples/CLAUDE.md](examples/CLAUDE.md) | Template for your own chief of staff config |
| [examples/scripts/briefing.py](examples/scripts/briefing.py) | Morning briefing generator |
| [examples/scripts/meeting_processor.py](examples/scripts/meeting_processor.py) | Transcript → facts + follow-ups pipeline |

### Deep Dives (new)
| File | What It Is |
|------|-----------|
| [memory-system.md](memory-system.md) | SQLite memory database, extraction protocol, effort tracking, semantic search |
| [learning-loops.md](learning-loops.md) | Reading system, content scout, discussion queue — feedback-driven learning |
| [discord-system.md](discord-system.md) | Discord bot, approval gates, message memory, fact extraction |

## Working Components

This repo is the architecture. The code for two of the pieces lives in standalone repos you can fork independently:

| Repo | What It Is | Where It Fits |
|------|-----------|---------------|
| [task-tinder](https://github.com/loganhc-09/task-tinder) | Swipe-based task triage with metacognition capture | The Tier 2 interface. You decide, the system learns your methods. |
| [reading-scout](https://github.com/loganhc-09/reading-scout) | Personal reading agent that learns from your conversations | The learning-loops layer. [More here](learning-loops.md). |

## Daily Surface

Most of the system runs in the background, but day-to-day I open a local web dashboard at `localhost:8091` (loopback only — bound to `127.0.0.1`, not exposed to your LAN). It's a small Flask server that pulls from the SQLite memory and queue tables and renders three panels: Task Tinder (the swipe UI for triage), Intel (overnight signals + reading), and a day-prep panel.

The full dashboard is custom to my workflow and not in this repo (yet). The Task Tinder swipe UI is open source at [task-tinder](https://github.com/loganhc-09/task-tinder) — fork that, point it at your own task store, and you have the most-used surface.

## Getting Started

You don't build this in a weekend. You build it one layer at a time.

1. **Day 0:** Pick your plan + skim cost-reduction habits ([details](getting-started.md#before-you-start-picking-your-plan-and-keeping-costs-down)) — 5 minutes
2. **Day 1:** Create your CLAUDE.md (10 minutes)
3. **Week 1:** Add memory files for persistence across sessions
4. **Week 2:** Morning briefing routine (manual first, then scripted)
5. **Month 1:** Scheduled scripts + SQLite memory database
6. **Month 2:** Discord bot for mobile access + approval gates
7. **Month 2:** Learning loops — reading system + content scout
8. **Month 3+:** The full stack — everything connected, everything learning

See **[getting-started.md](getting-started.md)** for the full walkthrough.

## Design Principles

- **Clarity beats code.** The bottleneck is never technical — it's knowing what you want.
- **Progressive complexity.** Each layer works on its own before you add the next one.
- **Close loops, don't open them.** Every automation should end with a verifiable outcome.
- **Human-in-the-loop by design.** Prep is automated. Decisions are not.
- **Memory is architecture.** If the AI doesn't remember yesterday, it can't help with tomorrow.
- **Learning compounds.** Systems that get smarter from your behavior beat static configurations.
- **Filter aggressively.** The value is in what you *don't* see — most content doesn't clear the bar.

## About

Made by [Logan Currie](https://logancurrie.com) with Claude Code.

Part of my series on building personal AI operating systems — [Captain's Log on Substack](https://loganinthefuture.substack.com/).

## License

MIT — use it, adapt it, build on it.

claude-chief-of-staff

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README