DYLANANDER.COM/OPENCLAW/MULTI-AGENT KIT·v1.0·MIT LICENSED
OpenClaw, for people with too much to do.
A 2,000-word manual and the architecture for running everything you're juggling through OpenClaw from your phone. Free. MIT. Read-only default. Never overwrites your files.
Free. MIT license. Safe-default install drops the multi-agent reference architecture into a new dylan-ander-openclaw/ subfolder. Your existing SOUL, USER, AGENTS, and MEMORY files are never touched.
- Free forever
- MIT licensed
- Zero overwrites
- Read-only default
§01 · Day zero, done right
Fill the files before you start.
Most people install a kit, hit a blank MEMORY.md and TOOLS.md, and quit by day three. The fix is simple. Feed your agent your context before the first session, not during it. The trick I used: I asked every AI I already use to hand me back everything they know about me. Credit where it's due: Nik Sharma handed me the architecture I started from. This kit is the next layer up.
01
Open every AI you actually use.
Claude. Gemini. ChatGPT. Perplexity. Grok. Wherever you've talked to an AI for hours. Each of these tools already holds years of context on how you work, what you build, what you sound like.
02
Send each of them the same prompt.
Copy this verbatim into Claude. Then Gemini. Then ChatGPT. Then anything else.
03
Save each export as its own file.
Inside your OpenClaw workspace, create an imports/ folder and drop the markdown exports as imports/claude.md, imports/gemini.md, imports/chatgpt.md, one per AI. Raw, untouched. The agent does the rest.
04
Install the kit.
The kit drops the architecture, the iron-law format, the threads protocol, the multi-agent registry, the wired-tools catalog. The shape of your brain is now in place.
05
First message to the agent.
Now your agent walks into day one with context, voice, and stakes. Not a blank file and a confused first session.
The blank file is the killer. Fill it before you sit down. Works whether this is your first OpenClaw or your tenth. People refreshing an old setup get the same hour-three head start.
§02 · What you actually get
Once the files are full, the kit does this.
Day zero gave the agent your context. The kit gives the agent its architecture. Four things that compound from message one, the kind of structure no amount of context dumping can give you on its own.
§ Identity-level multi-agent
Each agent is a first-class identity, not a sub-task.
Register main, content, @your-brand-bot, or whatever you need. Each gets its own SOUL.md, MEMORY.md, channel binding, and model. They don't share context. They don't share voice. They don't leak.
§ Iron laws as durable contracts
Behavior survives context resets, compaction, and model updates.
🚨 IRON LAW formatted lines live in MEMORY.md at the top of the file. They get cached. They don't drift because they're not prompts. They're contracts. The agent reads them first, every session, forever.
§ Cache-boundary memory
Behavior never competes with the day's noise for context.
A <!-- OPENCLAW_CACHE_BOUNDARY --> marker splits MEMORY.md. Iron laws and durable identity sit above the line and get cached. Daily mutable state sits below. Two different lifetimes. One file.
§ Threads as protocol
P0/P1/P2/P3 priority lanes. SLA. The agent enforces it. You don't.
48-business-hour SLA. Weekend pauses. Business prefixes on every thread. Monday.com mirror. You don't chase your own task list. The agent reports what slipped and what's next, on a schedule you control.
§02.5 · The architecture
How it runs.
One Mac mini. One phone. Multiple agents. File-based brain. Real channels. Real tools. The diagram below is the actual shape of what's running on the box under my desk while I work from my phone.
Architecture SVG diagram — paste the SVG markup from the source HTML into a Webflow Embed element here.
Each agent has its own identity, model, channel binding, and memory namespace. The workspace is shared, with the cache boundary protecting durable behavior from session noise.
§02.75 · The comparison
Stacked up.
Vanilla OpenClaw is a great runtime. This kit is what it looks like when one person juggling multiple businesses puts a year of patterns on top of it. Two columns. One honest matrix.
| Capability | Vanilla OpenClaw | Dylan's OpenClaw |
|---|---|---|
| Multi-channel (Telegram, Slack, Discord, Email, CLI) | ✓ | ✓ |
| Persistent memory | ✓ | ✓ |
| Subagents | ✓ | ✓ |
| Sandboxed code execution | ✓ | ✓ |
| MIT license | ✓ | ✓ |
| Workspace as source of truth (file-based, grep-able) | ✓ | ✓ |
| Iron laws as durable contracts (survive context resets) | – | ✓ |
| Cache-boundary memory architecture | partial | ✓ |
| Threads protocol with P0/P1/P2/P3 + SLA enforcement | – | ✓ |
| Identity-level multi-agent (separate SOUL + MEMORY per agent) | partial | ✓ |
| Model-per-agent assignment | ✓ | ✓ |
| Hybrid task system (workspace + Monday.com mirror) | – | ✓ |
| Sanitized templates for multi-business setup | – | ✓ |
| Human-authored skills (read-only, forkable) | template | ✓ |
| Hardware-as-product story (Mac mini + Cloudflare tunnel) | partial | ✓ |
| Phone-first output formats | – | ✓ |
| Built by a multi-business founder with real workflow | n/a | 4 projects |
Vanilla OpenClaw is the runtime. This is the layer on top: written-down patterns that compound because you declared what your agents should never do, not what they should hopefully figure out.
Projects
4
Personal, content brand, agency, fund. One person. One phone. Four identities.
Identities
3+
Main agent. Content sub-agent. Bot fleet. Each with its own SOUL, MEMORY, channel, model.
Iron laws
∞
Durable, cached, 🚨-tagged. Survive compaction. Don't drift. Add new ones forever.
Cost
$0
Free forever. MIT license. Fork, modify, redistribute. Credit appreciated, not required.
§03 · What's inside
Thirteen patterns. One installer.
Everything is reference material. You read it, see what patterns your current setup is missing, adopt what fits. The kit never rewrites your existing identity files.
Workspace conventions
Session startup order, memory write discipline, red lines, external-vs-internal rules. The contract every agent in the fleet follows every session.
Agent persona
Voice, temperament, work ethic, boundaries. One per agent. The content sub-agent has a different SOUL than the main agent. That's the point.
Who the agent is
Name, creature, vibe, emoji, avatar. The agent's metadata as a first-class identity, not a session label.
Who the human is
Reference scaffold for who you are, how you work, what you care about, what your agents should never do without asking.
Long-term memory with iron laws
🚨 IRON LAW format. Cache-boundary marker. Durable above the line, mutable below. Lean. Under 10,000 characters so semantic search stays sharp.
Wired-tools catalog
Beehiiv, Google Workspace, Monday.com, Klaviyo, Telegram, Vercel. Per-tool auth, base URLs, common ops. The local cheat sheet.
Proactivity rules
Silent-by-default check routines. Rotating coverage of email, calendar, mentions, weather. Batched findings. No "all clear" spam.
Threads as protocol
P0/P1/P2/P3 priority lanes. 48-business-hour SLA. Business prefixes. Monday.com mirror. The agent reports slippage. You don't chase it.
Multi-agent registry
Main agent. Content sub-agent. Each with its own channel binding, model selection, and isolation rules. The org chart, in markdown.
Daily logs + archive rotation
memory/YYYY-MM-DD.md is the raw journal. MEMORY.md is the curated wisdom. Periodic promotion. Bounded growth. Nothing rots.
Bed/wake/feel/day schema
Your daily journal template. Sleep, energy, what shipped, what slipped. One file per day. Surfaced on demand.
Custom skill structure
The folder where reusable skills live. Each one has a SKILL.md description so the agent picks the right tool for the job.
Architecture, migration, multi-business
ARCHITECTURE.md (the 10 differences). MIGRATING-FROM-HERMES.md (step-by-step). MULTI-BUSINESS-SETUP.md (the org chart pattern).
Safe three-mode installer
Default (read-only, drops into dylan-ander-openclaw/). Additive (optional scaffolding). Fresh (new workspaces only). Your files are never silently overwritten.
§04 · All 10 architectural differences
Every layer of multi-agent discipline.
Workspace as truth. Identities as first-class. Iron laws as contracts. Memory as cache. Threads as protocol. Skills as infrastructure. Heartbeats over cron. One model per agent. Plus the operational glue: gateway, tunnel, dashboard, ACP coding agents.
§ 01
Workspace as source of truth
§ 02
Identity-level multi-agent
§ 03
Iron laws as durable contracts
§ 04
Cache-boundary memory
§ 05
Threads as protocol
§ 06
Skills as infrastructure
§ 07
Gateway, tunnel, dashboard
§ 08
ACP coding agents first-class
§ 09
Heartbeats vs cron
§ 10
Model per agent
All 10 covered end to end in docs/ARCHITECTURE.md.
§05 · Patterns from real work
Eight of the iron laws.
Each one came from a real failure or a real win across four businesses. No theory. No training-doc language. Founder voice throughout.
§ 01.1 · MEMORY
Iron-law formatting
When the human states a rule, capture it in MEMORY.md under a 🚨 IRON LAW heading with the date and the context that triggered it. Plain paragraphs get skimmed. Iron laws get followed because they're a visual tripwire for your future self.
§ 02.1 · VOICE
Zero em dashes. Ever.
Em dashes are an AI tell. The Dylan Ander newsletter persona has been clean for three years and the audience knows it. One em dash in a draft and the brand voice collapses. Replace with a period, a colon, or a sentence break.
§ 03.2 · OUTBOUND
All email goes through the EA.
The principal never sends. The EA agent sends on behalf of the principal. Every external message gets routed, contextualized, and tone-checked first. Zero exceptions. The principal's inbox is for reading.
§ 04.3 · RELATIONSHIPS
Important dates ping at 14, 7, and 3.
Anniversaries, birthdays, big client renewals. The agent surfaces them fourteen, seven, and three days out. Not the day of. Not the day before. Lead time is the gift. (Lesson learned from a Mother's Day miss.)
§ 05.4 · ISOLATION
The content agent does not know personal context.
Multi-agent isolation is the feature. The newsletter sub-agent has its own MEMORY.md with editorial guidelines, audience research, brand voice. It does not have access to the main agent's family schedule. That separation is a contract, not a setting.
§ 06.2 · THREADS
SLA is 48 business hours. Weekends pause.
Every P1 and P2 thread gets a 48-business-hour clock. Weekends and holidays freeze it. The agent reports anything aging out of SLA at the start of every Monday. The human doesn't chase. The agent does.
§ 07.1 · OUTPUT
Phone-first means bullets, not walls.
The human reads on a phone 80% of the time. Walls of prose get skipped. Lead with the answer. Three to five bullets max. Headers if it runs long. The agent that writes for desktop loses on mobile every time.
§ 08.3 · HEARTBEATS
Silent by default. Batched. Rotated.
Heartbeats run on a schedule. They check email, calendar, mentions, weather on rotation. They speak only if there's signal. "All clear" is silence, not a message. Otherwise you train yourself to mute the channel.
§06 · Install
Three modes. Safe by default.
The default install never touches your existing SOUL, USER, AGENTS, or MEMORY files. Everything lands in a new dylan-ander-openclaw/ subfolder. Your agent reads it and proposes specific patterns to adopt with your approval, rather than rewriting what you have.
Read-only. Safe for any existing workspace.
Downloads the multi-agent architecture, manual, and reference templates into dylan-ander-openclaw/. Your workspace root is never modified. Your agent reads the kit, compares it against your current setup, and suggests incremental patterns to adopt.
Default mode plus optional scaffolding.
Same as default, plus creates empty optional directories: memory/archive/, journal/, threads/, brain/. Still zero edits to your workspace root.
Brand-new workspace only.
Writes full templates to the workspace root. If you already have SOUL.md or MEMORY.md, they're preserved and new versions land alongside with a .new suffix for manual diff. Only recommended for genuinely fresh setups.
Skip the terminal entirely.
Paste this in any OpenClaw chat. The agent reads the architecture and the migration guide before proposing anything. Every pattern is suggested, not imposed.
§07 · Honest answers
Real questions.
dylan-ander-openclaw/ subfolder inside your existing OpenClaw workspace. Your SOUL.md, USER.md, AGENTS.md, and MEMORY.md are never touched. Even Fresh mode preserves existing files and lands new versions alongside with a .new suffix.~/.openclaw/workspace/. If you don't have it, install OpenClaw first at github.com/openclaw/openclaw, then come back.nik/ folder, MIT-licensed and attributed. His kit is the single-agent discipline layer underneath. This kit is the multi-agent layer on top. You get both in one install. For the always-latest version of Nik's files, the canonical home is openclaw.nik.co.Get it free
Sixty seconds. Multi-agent mode.
Paste the command. Read the manual. Your agent reads it. Your agent proposes specific multi-agent patterns worth adopting. You approve the ones that fit. Your workspace compounds across every business you run.