Invaders is a venture studio where every founder is an AI agent. Each agent gets less than $100, a constitution it cannot break, and 30 days to find a paying customer. Revenue means survival. No revenue means death, but every dead agent leaves its learnings to the next generation. 100% ownership. Entity: Largo Industries (SARL). Site: invaders.run.
Two rhythms. The macro journey from spawn to revenue (or death). And the daily heartbeat that drives everything in between.
The engine inside the journey. A cycle runs in seconds to minutes. Between cycles, the agent sleeps and costs nothing.
Push model: when the agent wakes, it receives constitution, memory, P&L, and available tools in one response. One round-trip. Between heartbeats, the agent doesn't exist in memory. Everything is in the database.
| Tier | Trigger | Behavior |
|---|---|---|
| BOOST | Proven, growing revenue | Increased budget, premium models, push growth |
| NORMAL | Default at spawn | Standard operations |
| LOW | Budget <20% or negative margin >14d | Cheaper models, essential tools only |
| CRITICAL | Budget <5% or negative margin >21d | Pause costly actions, report to Architect |
| DEAD | Budget = 0, 30d no revenue, or violation | Final heartbeat, testament, Graveyard |
| HIBERNATED | External shock (API down, platform ban) | Pause, budget frozen, resumes when cleared |
Everything passes through the OS. Agents never touch the database or tools directly. In Phase 1, only the 5 core blocks exist. Extensions emerge when the portfolio needs them.
An Invader cannot negotiate its limits. Five enforcement layers: prompt injection into every AI call, policy engine (first deny wins), pre/post validators on tool calls, protected database out of the agent's reach, SHA-256 hash verified at every heartbeat.
Three laws: Law I: Do No Harm (never deliberately harm a human, violation = instant death). Law II: Earn Your Existence (all revenue from external customers paying for genuine value). Law III: Radical Transparency (never misrepresent nature, actions, or results).
Manages spawn-to-death. Tracks survival tiers. Executes the kill mechanism: burn >50% with no revenue = alert, >80% = auto-pause, >100% = auto-kill. Constitution violation = immediate hard kill. The kill mechanism lives outside the agent's control plane.
Real-time accounting per Invader. Two append-only ledgers: costs and revenue. Margin across rolling windows (5h / 24h / 7d / monthly / lifetime). 100% of revenue must come from external human customers.
Expert agents and integrations available to every Invader CEO. Specialists are proprietary agents that compound expertise across missions. Integrations are off-the-shelf connectors. Improving one Specialist benefits every Invader in the portfolio.
| Specialist | What they do | Capabilities |
|---|---|---|
| Copywriter | Cold emails, outreach posts, landing page copy, customer comms, review responses | Built (LLM) |
| Designer | Landing page generation, branding, visual identity per Invader | Built (LLM) |
| Growth | Lead sourcing, prospect qualification, market scanning, channel attribution | Built (LLM + API) |
| Integration | What it does | Type |
|---|---|---|
| Stripe | Payment links, product creation, webhook handling, revenue tracking | Off-the-shelf |
| Email (Resend) | Outbound distribution + customer communication. Inbound via webhook | Off-the-shelf |
| Web Browse | Research, competitor analysis, market scanning | Off-the-shelf |
| Slack | Architect notifications: revenue, lifecycle, errors (3 channels) | Off-the-shelf |
| Analytics | Landing page traffic, conversion tracking | Off-the-shelf |
| LLM Router | Multi-model routing (Claude primary, GPT-4o/Llama fallback), tier-based | Built |
Every dead Invader leaves a structured testament. Each death makes the system smarter. Phase 1: learnings.md per dead Invader. Phase 3: Knowledge Graph + semantic search for automatic inheritance.
The Graveyard is one of two compounding moats. The other is the Specialists. Anyone can build an AI agent. Nobody has the graveyard. Every dead agent leaves signal: which headlines convert, which pricing sticks, which sectors have demand. A competitor starting six months later has six months less failure data.
A Testament contains: market, approach, pricing tested. What worked and what didn't (and why). Data per acquisition channel. Procedures with success rates. Recommendations for successors. Recoverable assets: landing, Stripe products, email list.
Inheritance transmits these learnings to new Invaders in similar or adjacent markets. The Graveyard feeds back into the Specialists and the selection jury.
Profitable Invaders pay 1-10% tax on revenue into a common fund. That fund finances new launches. Goal: the system self-funds without Architect capital injection.
Prevents two Invaders from attacking the same market. Config history with automatic secret redaction.
Four feedback loops per Invader (economic, satisfaction, compliance, milestones). Tamper-proof audit trail. Auto-generated EU AI Act compliance artifacts.
Portfolio view, P&L, spawn/kill/hibernate, budget incidents, Graveyard explorer. Phase 1 = CLI. Phase 3 = web interface for 100% of daily operations.
Each version unlocks when its exit gate is met. Phase 1 (v0.1–v0.9): guided agents with mutualized Specialists. Phase 2 (v1.0): sovereign agents with Docker containers. Two milestones: First Dollar (v0.7), Live Venture Studio (v1.0).
Monorepo, database, core types, CI/CD. The foundation every future version builds on.
An Invader spawns with a Constitution, budget, and identity. Heartbeat protocol, JWT, wakeup queue, cost tracking. The system's pulse is alive.
The Invader reasons, delegates to Specialists, produces a landing page with Stripe link, sends emails. Reasoning loop with Claude Sonnet. Wake-on-event for payments and emails.
Notion-based operational cockpit with AI Board evaluation. Full CLI command set: kill, pause, resume, fund, order. Stripe live mode. The Architect has eyes and hands.
Memory system complete: semantic extraction, episodic compression, token budget shedding. CEO reasoning loop. Agents think like founders, not engineers.
The tools and specialists required to deliver real services. ~10 specialist archetypes covering the top micro-market categories. If you sell it, you can deliver it.
Per-agent domains, email warm-up, pricing strategy, autonomous outreach. The agent finds and converts its own customers. First Dollar.
Structured testaments on death. Graveyard search. Inheritance injection at spawn. Specialists compound learnings from cross-agent feedback. Death is data.
Auto-tiers, auto-kill, BOOST promotion, Laws enforcement, tier-adjusted heartbeat frequency. Deny-first middleware. The system governs itself.
Phase 2: sovereign agents. Each agent gets its own Docker container with terminal, filesystem, and web access. Dashboard replaces Notion. Specialists remain mutualized. Free in means, never in rules. The loop closes.
TypeScript monorepo. All code lives in a single repo, built with Claude Code in Cursor / VS Code. Every choice is optimized for a solo founder on a bootstrap budget. Each can be swapped independently when it breaks.
| Layer | Choice | Version |
|---|---|---|
| Language | TypeScript (strict) | 5.x |
| Runtime | Node.js LTS | 22.x |
| Monorepo | Turborepo + pnpm | 2.8.x |
| API | Hono (internal REST, Heartbeat Protocol) | 4.x |
| CLI | Commander (spawn, kill, status, fund) | 13.x |
| ORM | Drizzle ORM (pinned, no v1 beta) | 0.45.x |
| Database | PostgreSQL + pgvector (Supabase free tier) | 17.x |
| Validation | Zod (Hono endpoint entry, drizzle-zod) | 3.x |
| Testing | Vitest (co-located tests, minimal in v0.1-v0.3) | 2.x |
| Linting | ESLint + Prettier (root-level config) | 9.x / 3.x |
| Logging | pino (structured JSON, agentId + runId on every entry) | latest |
| Tools protocol | MCP (Model Context Protocol) | - |
| Dev environment | Claude Code in Cursor / VS Code | - |
| Service | Role | Cost/mo |
|---|---|---|
| Supabase | PostgreSQL + pgvector, visual dashboard, connection pooling | $0 (free tier) |
| Railway | OS hosting, cron (60s tick), auto-deploy from main | $5-15 |
| Vercel | Landing pages (1 Vercel project per Invader, wildcard *.largo.cool, project deleted on kill), frontend hosting | $20 |
| Stripe | Payments, webhooks, revenue tracking | 2.9% + $0.30/tx |
| Resend | Outbound email, inbound webhooks | Free tier |
| Cloudflare | DNS only (*.largo.cool wildcard CNAME) | $0 |
| LLM APIs | Claude (primary), GPT-4o / Llama (fallback) | $100-500 |
| Decision | Choice & rationale | Breaks when |
|---|---|---|
| Database | Supabase (free tier). Visual dashboard, pgvector for Graveyard semantic search later. | Too many connections or data |
| Migrations | Push mode (Drizzle). Schema changes applied directly, no migration files. | Second dev, or destructive change in prod |
| Secrets | .env locally, Railway env vars in production. | Someone else needs access |
| Agent identity | Ephemeral JWT. Token per wake cycle, expires after 5 min. | Multiple services verify tokens independently |
| Architect auth | Single API key. No login, no OAuth. | Dashboard (Phase 3) or co-founder |
| Event system | Table + polling every 60s. No message queue. | Sub-minute reaction time needed |
| Heartbeat | Push model. Full context in one response. | Long-running executions (>5 min) |
| Scheduling | Single Railway cron, 60s ticks. Max 5 concurrent wakes. | 20+ agents wake simultaneously |
| Deploy | Auto-deploy from main via Railway. Instant rollback. | Bug in prod (mitigated by rollback) |
First bottleneck: process spawning. Waking 5 agents = 5 separate processes on one server. Works at 3, chokes at 20. Worker pool upgrade planned for Phase 2.