Home
Stack The bespoke core · everything else plugs into it

Twenty-plus systems. Two of them are ours.

Most of this page is commodity — models, cloud, databases you could subscribe to tomorrow. The leverage is the two systems we built ourselves: Zeus runs the agents, Alexandria holds the memory. Everything else on the page plugs into them — routed, remembered, coordinated. No logo wall. No vendor pitch. Just the architecture.

The core Two bespoke systems · in production · dogfooded daily

Two systems we built. Everything else plugs in.

Every model, store, and tool further down this page sits behind the core. Zeus decides who works and how; Alexandria is what they remember. The third-party systems below do the heavy lifting — the core is what makes them a single operation instead of a pile of subscriptions.

Layer 01 · Models Foundation models · routed per task

Pick the right brain. For each job.

Different models are good at different things. Reasoning, coding, voice, search, vision, low-latency. The trick is routing each task to the right model and not paying premium prices for tasks a smaller model handles fine.

Anthropic · Claude Primary reasoning, long-context architecture work, agentic code, sensitive client work.
Google · Gemini Multimodal tasks, large-document ingestion, complementary reasoning.
OpenAI · Codex Code-focused completion lanes inside the build pipeline.
Perplexity Live web research with citations — agents call it for fresh-data lookups.
Qwen Alternative reasoning + cost-efficient inference for high-volume agent tasks.
DeepSeek Cost-efficient reasoning for high-volume tasks where Anthropic is overkill.
ElevenLabs Voice synthesis for any agent that needs to speak — client-facing, content, calls.
Layer 02 · Orchestration The core coordinator · harnesses · routing

The coordinator. And the environment.

Models alone don’t do work. Agents do. And agents need two things this layer provides: Zeus, the coordinator every agent runs under, and an environment where agents live. We run production on our own harness — built for our standards of quality and performance — and we work natively inside the harnesses clients already have.

Zeus The bespoke core of this layer — the coordinator every agent runs under. Roles, lifecycle, learning loops. See the venture →
Custom harness The production environment we run on — built for our standards of quality and performance, coordinated by Zeus.
MyCLAW Agentic environment harness we know deeply and operate in natively — when a client’s stack or deliverable already lives on it.
OpenCLAW Open variant of the same family — the same native familiarity for cases that ship on it.
OpenRouter Model-routing layer — one call surface, many models, cost & latency optimised per task.
Direct API calls For the tasks where OpenRouter overhead doesn’t pay — we go direct to provider APIs.
Custom model orchestration Multi-model pipelines, eval rigs, retry & fallback logic, agent hand-off, lineage.
Layer 03 · Infrastructure Cloud · compute · uptime

Where the systems actually run.

AWS Primary cloud — compute, storage, networking, deployments, observability.
DigitalOcean Lighter-weight services, isolated workloads, simpler provisioning where AWS is overkill.
Layer 04 · Data + Knowledge The core memory · stores · embeddings

Agents don’t read files. They ask Alexandria.

Alexandria The bespoke core of this layer — every artifact stored once, indexed automatically, queried by any agent over MCP. See the venture →
Supabase Application database + auth + edge functions for production apps.
MySQL Transactional data where the SQL is mature and the schema is established.
Obsidian Second brain — knowledge, briefs, drafts, project memory. Alexandria ingests it; agents query through Alexandria.
Notion Client-facing deliverables, structured docs, runbooks. Agents draft; human reviews.
Layer 05 · Ops + Automation Project mgmt · productivity · browser automation

The connective tissue. Where humans and agents meet.

Plane Project management — tickets, roadmaps, sprints. Agents move tickets; humans set priority.
GSuite Calendar, mail, drive — where the operator’s day actually lives. Agents read, write, schedule, send.
Playwright Browser automation — agents drive web UIs where there’s no API: scraping, form-filling, testing.
Interconnect How it all stays glued together

The hard part isn’t the tools. It’s the seams.

Anyone can subscribe to all the systems on this page. The leverage is what you can’t subscribe to — the seams, and the core the seams run through. Every task routes through Zeus; every agent reads and writes Alexandria. Model routing decisions, eval rigs, lineage tracking, deployment gates, secrets management, error handling, retry logic, cost monitoring, observability, hand-off contracts, runbook automation, sub-agent dispatch — all coordinated by the core, not bolted on.

That’s the work. Every case on /cases runs on this stack — the differences between them are which layers carry more load, which models route where, and which agents Zeus coordinates. The Audit maps your version of this. The Sprint builds it. The Retainer runs it.