Coming June 1, 2026

The AI operating system
for developers.

Every other AI coding tool locks you into a single provider at a single price. Your MacBook can run models that handle 70% of your work for free. Olympus routes work across Claude, GPT, local Ollama, and any OpenAI-compatible provider — automatically, cost-aware, offline by default.

Get started free Try the demo →
$ brew install convergent-systems-co/tap/olympus

How It's Different

Not another AI wrapper. A complete orchestration layer.

GitHub Copilot Cursor Claude Code Olympus
Cost to start $19/mo $20/mo Pay per token Free
Models GPT + Claude Multiple (you manage keys) Claude only All providers + your local GPU
Works offline No No No Yes, fully
Session memory None None Session only Persistent, tiered
Governance None None None Structural panels

Memory that follows you

Context that persists — local, cross-machine, team-wide, or org-wide.

Free
Local Session Memory

Your context is saved on this machine. Pick up exactly where you left off — same project, same thread, same decisions.

Pro
Cloud-Encrypted Sync

Your context follows you across machines. Switch from laptop to desktop — Olympus knows exactly where you were.

Team
Shared Project Memory

Your whole team shares project context. New teammate joins — they have the work decisions, patterns, and standards immediately.

Enterprise
Org-Wide Cascade

Standards set at the org level propagate to every team and every session automatically. One policy, every developer.

Mid-task. Switch machines. Open your terminal. Olympus knows exactly where you were.

The Pantheon

A complete system, not a wrapper. Each module has one job.

Zeus Orchestrates your request across the full system
Athena Understands what you're asking and routes to the right capability
Hephaestus Generates code changes, applies patches, verifies the build
Aegis Inspects every input and output for security issues
Mnemosyne Remembers your context across sessions, machines, and teams
Apollo Selects the right model for each task based on cost and complexity
Iris Routes to the right provider — local first, cloud when necessary
Argus Monitors cost, flags anomalies, enforces budget limits
Hermes The internal event bus — coordinates every module in real time
Prometheus Runs the agentic loop — plan, execute, verify, retry
Cerberus Gates every dispatch — checks capacity, cost approval, and coverage
Epimetheus Learns from every session — traces cost trends and fallback patterns
Pythia The release gate — verifies intent, process, outcome, and integrity

Constitutional Governance

Other tools let you write a prompt that says “don’t do anything risky.” Olympus enforces policies as runtime system behavior — signed verdicts, automated review panels, rules that run before code is applied. A structural rule cannot be bypassed with a prompt.

  • Security review
  • Architecture validation
  • Threat modeling
  • Cost analysis
  • License compliance
  • Performance audit

All automated. All auditable. Signed emission logs for every action. Customize or extend with your own policies.

☉ Security
▢ Architecture
⚠ Threat Model
$ Cost
⚡ Performance
☑ Compliance
Custom policies supported

Pricing

Start free with local models. Scale when you need cloud.

Monthly Annual Save 10%
Free
$0
  • All Pantheon modules
  • Local LLMs unlimited (Ollama)
  • Cloud Ollama when local hardware can't keep up
  • Cloud access via Drachma (pay-as-you-go)
  • Local persistent memory
  • Basic governance panels
Get Started
Most Popular
Pro
$9 /mo
  • Everything in Free
  • Cloud memory sync (coming Q3)
  • Cross-machine session resume (coming Q3)
  • Custom governance policies
  • 20 Drachma included monthly
  • Advanced models (GPT-5.4, Claude Sonnet, o4-mini)
Team
$29 /seat/mo
  • Everything in Pro
  • Shared team context (governance rules, routing config)
  • Shared team memory (coming Q3)
  • Team governance enforcement
  • 50 Drachma/seat included monthly
  • Premium models (GPT-5.4 Pro, o3)
  • Priority support
Enterprise
Custom
  • Everything in Team
  • Org-wide cascading memory (coming Q3)
  • Org-wide governance cascade (coming Q3)
  • Custom Drachma volume pricing
  • All models including GPT-5.4 Pro
  • Dedicated support + SLA (coming Q3)
Contact Sales

What is Drachma?

When cloud models are needed, Olympus handles the provider accounts. You buy Drachma — one balance, one bill. Olympus routes the call and pays the provider. You never manage API keys or worry about which provider’s billing dashboard to check.

30 Δ $5 Starter
100 Δ $12 Developer
500 Δ $50 Builder

Per-model rates available in your portal after sign-in.

☁

Can't run local models?

If your machine doesn't have the GPU or RAM to run Ollama models locally, Olympus offers Cloud-Based Ollama — the same open-weight models (Llama, Qwen, Mistral) hosted for you, billed at standard Drachma rates. Same models, same quality, no hardware requirements.