Briefed

A daily newsletter digest pipeline + local web reader. Gmail → Haiku summaries → web app → notification ping.

Architecture

[Gmail]
   ↓  pre-fetch.py (fetches, filters, extracts compact metadata)
[newsletter-inbox.json]
   ↓  Haiku cron agent (reads compact JSON, writes AI summaries)
[newsletter-today.json]
   ↓  fetch-bodies.py (adds full HTML email bodies)
[newsletter-today.json + bodies]
   ↓  Express web reader (default port 3001)
[Notification ping → user opens reader]

Why split fetch/summarise? Raw Gmail API JSON overflows Haiku's context. Python handles data wrangling; Haiku handles cognition.

Security & Scope

• Gmail access is read-only (gmail.readonly).
• OAuth token is stored locally at ~/.openclaw/workspace/briefed-gmail-token.json (or BRIEFED_GMAIL_TOKEN_FILE).
• The workflow should only read/write the following workspace files:
  • newsletter-inbox.json
  • newsletter-today.json
  • newsletter-interests.json
  • newsletter-notes.json
  • reading-list.md
• Do not send newsletter content to external endpoints other than the configured model provider and user-selected notification channel.

Prerequisites

• Python 3.9+
• Python deps for Gmail API (google-api-python-client, google-auth, google-auth-oauthlib)
• A Google OAuth Desktop client JSON file (for Gmail read-only auth)
• Node.js ≥18 (for the reader web app)
• claude-haiku-4-5 on the OpenClaw models allowlist
• A notification channel configured in OpenClaw (Telegram, Discord, etc.)

Setup

1. Install Python dependencies

cd ~/.openclaw/workspace/briefed
python3 -m pip install -r scripts/requirements.txt

2. Configure Gmail OAuth

Create a Google Cloud OAuth Desktop app and download the client JSON, then set:

export BRIEFED_GMAIL_CLIENT_SECRET=~/client_secret.json

On first script run, Briefed opens a browser OAuth flow and stores a reusable token at:

~/.openclaw/workspace/briefed-gmail-token.json

3. Deploy the reader app

# Copy the reader to the workspace
cp -r assets/reader/ ~/.openclaw/workspace/briefed/
cd ~/.openclaw/workspace/briefed
npm install

4. Configure Gmail token paths (optional)

Defaults (works for most users):

• Token file: ~/.openclaw/workspace/briefed-gmail-token.json
• Client secret: ~/client_secret.json

Override via env vars if needed:

export BRIEFED_GMAIL_CLIENT_SECRET=~/path/to/client_secret.json
export BRIEFED_GMAIL_TOKEN_FILE=~/.openclaw/workspace/briefed-gmail-token.json

5. Configure interests

Create ~/.openclaw/workspace/newsletter-interests.json (or let it be auto-created on first run):

{
  "version": 1,
  "topics": { "ai": 0.9, "startups": 0.8, "design": 0.75 },
  "signals": [],
  "sources": {}
}

6. Start the reader

Run manually if you prefer no persistence. LaunchAgent is optional convenience for auto-start.

# Quick test
node ~/.openclaw/workspace/briefed/server.js

# Persistent — create ~/Library/LaunchAgents/ai.openclaw.briefed.plist

LaunchAgent plist template:

\x3C?xml version="1.0" encoding="UTF-8"?>
\x3C!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
\x3Cplist version="1.0">\x3Cdict>
  \x3Ckey>Label\x3C/key>\x3Cstring>ai.openclaw.briefed\x3C/string>
  \x3Ckey>ProgramArguments\x3C/key>\x3Carray>
    \x3Cstring>/usr/local/bin/node\x3C/string>
    \x3Cstring>/Users/YOUR_USER/.openclaw/workspace/briefed/server.js\x3C/string>
  \x3C/array>
  \x3Ckey>EnvironmentVariables\x3C/key>\x3Cdict>
    \x3Ckey>BRIEFED_GMAIL_CLIENT_SECRET\x3C/key>\x3Cstring>/Users/YOUR_USER/client_secret.json\x3C/string>
    \x3Ckey>BRIEFED_GMAIL_TOKEN_FILE\x3C/key>\x3Cstring>/Users/YOUR_USER/.openclaw/workspace/briefed-gmail-token.json\x3C/string>
  \x3C/dict>
  \x3Ckey>RunAtLoad\x3C/key>\x3Ctrue/>
  \x3Ckey>KeepAlive\x3C/key>\x3Ctrue/>
  \x3Ckey>WorkingDirectory\x3C/key>\x3Cstring>/Users/YOUR_USER/.openclaw/workspace/briefed\x3C/string>
  \x3Ckey>StandardOutPath\x3C/key>\x3Cstring>/tmp/briefed.log\x3C/string>
  \x3Ckey>StandardErrorPath\x3C/key>\x3Cstring>/tmp/briefed.log\x3C/string>
\x3C/dict>\x3C/plist>

launchctl load ~/Library/LaunchAgents/ai.openclaw.briefed.plist

7. Create the daily cron job

Use the OpenClaw cron tool with this agent prompt (fill in the placeholders):

Run my daily newsletter digest. Follow these steps exactly:

## Step 1 — Pre-fetch emails
Run: python3 ~/.openclaw/workspace/briefed/scripts/pre-fetch.py

## Step 2 — Read the compact inbox
Read: ~/.openclaw/workspace/newsletter-inbox.json

## Step 3 — Write newsletter-today.json with AI summaries
For each newsletter, write to **only** this file: ~/.openclaw/workspace/newsletter-today.json.
Do not modify any other files in this step.
Use the snippet field to write real summaries — do NOT just repeat the subject line.
Score by interest: (adjust topics and weights to match your interests)
  ai/ml=0.9, startups=0.85, design=0.8, finance=0.75, general=0.6

Schema per story:
{ "id", "rank", "source", "subject", "headline", "summary", "bullets": [], "threadId", "gmailUrl", "score", "body": "" }

## Step 4 — Fetch HTML bodies
Run: python3 ~/.openclaw/workspace/briefed/scripts/fetch-bodies.py

## Step 5 — Send notification
Send (via your configured channel):
"📬 Today's digest is ready — \x3CN> stories waiting.\
→ http://YOUR_HOST:3001"

## Step 6 — Final reply
📬 *Briefed — [DD Mon YYYY]* · \x3CN> stories
*\x3Crank>. \x3CSource>* — \x3CHeadline>
\x3COne sentence summary>
(repeat for all stories)
_Open the reader → http://YOUR_HOST:3001_

Before enabling cron, run this once manually to complete OAuth in a browser:

python3 ~/.openclaw/workspace/briefed/scripts/pre-fetch.py

Cron schedule: 0 7 * * * (7am daily), model: anthropic/claude-haiku-4-5, delivery: announce.

Data Files

All data files live in ~/.openclaw/workspace/:

Reader API

Filtering Transactional Email

scripts/pre-fetch.py has two tunable lists near the top:

• SKIP_SUBJECT_PATTERNS — subject substrings that flag an email as transactional
• SKIP_SENDERS — sender names that are always transactional (e.g. banks, shops)

Tune these when transactional emails slip through.

Branding

The reader shows "Briefed" with a blue "B" logo by default. To customise, edit public/index.html and public/icon.svg.