Skip to content

Navigation Menu

Sign in
Sign up
@ShayanSpiel
ShayanSpiel
Follow

Shayan Spiel ShayanSpiel

🎯
Focusing
Agentic Solutions Architect · Marketing Strategist → Systems Builder

Block or report ShayanSpiel

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ShayanSpiel /README.md

Shayan Spiel

Founder of SpielOS — an AI Company Operating System · AI implementation for businesses that already work

I take the repetitive work your team still does by hand — intake, delivery, support, reporting, scheduling, bookkeeping runs — and turn it into supervised AI workers that run it every day, with humans in charge.


What SpielOS does

Two problems, one monthly rate:

Service What it means
🤖 AI Workers Hand repetitive business work to supervised AI agents — agentic workflows that execute real operations, not chat demos
🔧 AI DeSlopping Fix broken AI-built software — fragile, confusing tools that became hard to maintain get rebuilt into systems that hold

2,990ドル/month · One active build at a time · No hourly billing, no lock-in

👉 Start here: Apply — Free Review

Free review · No required call · See the scope before you pay

You describe what keeps breaking or what eats your team's hours. You get a clear scope and result before any build starts — and before any payment.


Who this is for

Established online businesses and service providers that already have real customers, an active website, and a working sales or delivery funnel — but are doing too much repetitive knowledge-work manually:

  • Ecommerce brands & marketplaces
  • Travel companies
  • Agencies & consultancies (non-AI)
  • Coaches & education businesses
  • Accounting & bookkeeping firms
  • Online service businesses & SaaS with real operations

Typically 1ドルM–25ドルM+ annual revenue. The buyer is the person who owns the operation and the money — owner, CEO, COO, senior operator. Technical expertise is neither required nor assumed.

Not a fit: pre-revenue startups looking for "an AI idea," or people who want to build their own agent system. This is for operators who want the work done.


Proof: we run on AI ourselves

SpielOS is not a slide deck. The company itself runs through supervised AI departments — goals, runs, approvals, evidence, reports. The live company record is public:

📊 See it running → spielos.xyz/live


How it works

  1. Apply — Free Review — describe one workflow that keeps breaking or eats hours
  2. Review & Agent Brief — we map the loop and define the scope, in plain language
  3. Build — one active build at a time, measured against your output, quality, and cost
  4. Handover — workers keep running; you see the numbers, not the plumbing

The full model — Director, Departments, Workflows, Agents, Evals — is documented openly: How SpielOS works →

Real department use cases (Design, Content, Marketing, SEO, Analytics): spielos.xyz/solutions →


Pricing

One monthly rate, built around results, not hours:

2,990ドル/month — one active build at a time →

Applying comes before payment. Pricing exists to support the decision, never to lead it.


Open source: AI workers & departments

Everything below comes out of one system — SpielOS, an open-source AI company operating system — decomposed into standalone workers you can run yourself. Every worker installs with one pasted command into Claude Code, OpenCode, or Codex CLI — and works immediately. No servers. No accounts. Your data never leaves your machine.

Want the same workers built, supervised, and measured for your business? That's the paid sideApply — Free Review.

📡 Outbound automation department

Project What it does
Lead Researcher — AI lead research agent Give your AI assistant one job: find N qualified leads from your Ideal Customer Profile and don't stop until it's done. Evidence-checked, batch loop, survives restarts.
Social Lead Researcher LinkedIn lead research agent Find qualified LinkedIn & X prospects from your ICP and don't stop until it's done. Research-only, recent-signal-backed, human decides contact.
Email Outreach Agent cold email automation agent Your AI drafts personalized emails from real research; YOU approve each one; nothing ever auto-sends. Pairs with Lead Researcher for a fully local outbound pipeline.

🔍 SEO automation department

Project What it does
AI Keyword Research Agent AI keyword research automation skill Give your AI assistant one job: find N real keyword opportunities for your business and don't stop until it's done. Clustered, intent-scored, evidence-backed — zero invented volume, no API keys.
SEO Audit Agent automated technical SEO audits Your AI fetches live pages and collects facts; a deterministic engine scores them (same facts = same verdict) and writes the prioritized fix report. Read-only by design.

✍️ Content production department

Project What it does
Content Production Agent AI content pipeline agent Deep, structured articles written to your voice file; AI-slop patterns rejected by the engine; you approve every piece before it ships.

📊 Analytics department

Project What it does
Analytics Agent marketing analytics automation Your AI runs real queries in PostHog/GA4/Search Console and records results with full provenance (source + exact query). No invented numbers.

🧰 Cross-cutting tools & skills

Project What it does
Skills — agent skills library Production-grade skills for content writing, translation, SEO, analytics, design systems, video creation. Ready to drop into any agent.
CacheCatch — prompt cache audit tool Audits AI agent context and shows what to move so repeated tokens hit cache — finds hidden agent cost leaks.
SpielOS — AI company operating system The whole harness: Goals, Runs, Workers, Departments, Evals, one Director loop (OBSERVE → DECIDE → ACT → EVALUATE). Install: pipx install spielos && spielos init
homebrew-spielos Homebrew tap for SpielOS: brew install ShayanSpiel/spielos/spielos
SpielOS Workers — AI automation playbook catalog Copy-paste recipes that turn your AI coding assistant into an invoice-processing, client-onboarding, lead-qualification, Notion/Gmail/HubSpot automation builder — 22 real client workflows documented step by step.
Experiments & history
Project What it is
vibebaba An abandoned open-source vibe-coding platform experiment — kept public as a field record. If your own vibe-coded project ended up like this, that's literally the DeSlopping problem.
ShayanWiki Markdown-based wiki with content pipeline.
SpielCLI Earlier generation of the marketing-team-in-your-IDE idea. Superseded by SpielOS.

Links

🌐 Website spielos.xyz
✉️ Apply — Free Review spielos.xyz/apply
📋 Services spielos.xyz/services
📊 Live company record spielos.xyz/live
🐦 X / build logs @ShayanSpiel

Build a business that runs without you.

Apply — Free Review →

Pinned Loading

  1. CacheCatch CacheCatch Public

    CacheCatch audits AI agent context and shows what to move so repeated tokens hit cache instead of full-price input — it finds context waste, prompt cache misses, and hidden agent cost leaks; and gi...

    TypeScript 1 1

  2. Lead-Researcher Lead-Researcher Public

    Give your AI coding assistant a job: find 2000 qualified leads from your ICP — and don't stop until it's done. Works with Claude Code, OpenCode, Codex.

    Python

  3. ShayanWiki ShayanWiki Public

    Markdown-based wiki and content pipeline for the SpielOS ecosystem — turns docs and work sessions into structured, on-voice knowledge. See spielos.xyz.

    Python

  4. Skills Skills Public

    Production-grade agent skills for content writing, translation, SEO, analytics, design systems, video creation, and more. Ready to customize.

    HTML

  5. vibebaba vibebaba Public

    An stale, vibecoding platform experiment which is ended.

    TypeScript

AltStyle によって変換されたページ (->オリジナル) /