Cut your OpenClaw API costs by 50-80%
Without changing your code.
“I was spending $200/month on Claude API calls for my coding agent. After installing RelayPlane, it dropped to $87. Same quality output—it just stopped using Opus for simple tasks like file reads and status checks.”
Matt Turley
Founder, RelayPlane · 20 years building software
Yes, this is the founder's own story. Early user testimonials coming soon.
We use OpenClaw daily. This exists because we needed it.
See exactly what you're saving
Real-time visibility into every request, model selection, and dollar saved.
Track savings, monitor routing decisions, and optimize your agent fleet — all in one place.Available on Pro and Max plans.
Running a team of agents burns through credits fast.
Every file read, status check, and simple task hits your Opus quota—even when a cheaper model would work just fine.
How intelligent routing actually works
The Swarm learns from anonymized patterns across all users—task types, token counts, success rates—never your actual prompts. Think Waze for API routing.
The Swarm explained in 3 sentences
Analyze metadata
Looks at task type, token count, and complexity signals — never your actual prompts.
Check patterns
What worked for similar requests across all users? “Code review under 3K tokens succeeds 94% on Haiku.”
Pick optimal model
Chooses the cheapest model that meets your quality threshold — if you need 95% success, it won't risk 87%.
Network effect
Every user (free or paid) contributes anonymized success/fail data. More users = smarter routing for everyone. We're early—currently 50+ beta users contributing routing data.
What if routing picks the wrong model?
This is the fear everyone has. Here's exactly what happens.
Scenario: Haiku returns garbage
Worst case: You paid for both calls. Still cheaper than always using Opus.
Built-in fallback chains
Circuit breakers: If a model fails 5x in a row, we skip it automatically for 30 seconds.
The math still works: Even with occasional fallback calls, users save 50-80% because most simple tasks do succeed on cheaper models. You're not paying Opus prices for file reads.
Local Ledger Learning
Your proxy gets smarter over time—learning from your usage patterns, stored entirely on your machine.
What the Ledger captures
Every run, every decision, every outcome
Task patterns
Code review, file reads, complex reasoning
Success rates
Which model worked for which task type
Timing data
Latency, time-to-first-token, retries
Cost trends
Spend by model, task type, time period
How it makes routing smarter
Pattern recognition, local-first
100% local. Zero cloud dependency.
SQLite database on your machine. Works offline. Yours to export.
Week 1
Rule-based routing
Week 4
Personalized routing
50%+ savings
Free tier, no cloud needed
Start saving in 60 seconds
Three steps. Zero code changes.
Install the proxy
npm install -g @relayplane/proxyMIT licensed. Runs 100% locally.
Point your agent at it
export ANTHROPIC_BASE_URL=localhost:3001One environment variable. No code changes.
Watch your costs drop
relayplane statsReal-time dashboard shows exactly what you're saving.
More than just a proxy
RelayPlane is a complete agent operations platform. Here's what's built and ready.
Policy Engine
Complete control over which models can be used, when, and by whom. Set allowlists, blocklists, cost thresholds, and approval requirements. “Never use GPT-4 for customer data” — enforced automatically.
Included in Max tier
Compliance & Audit
Decision Audit Trail
Know exactly why each call was routed where it was. Full explainability for compliance.
Approval Gates
Require human approval for expensive operations. Multi-approver workflows.
Operations & Cost Control
Budget Controls
Hard limits by day/week/month. Get alerts before you blow through spend.
Pattern Detection
Spots anomalies, cost spikes, and failure patterns. Suggests optimizations.
Team Collaboration
Teams & Workspaces
Multi-user access with role-based permissions. Shared learnings across team agents. Separate budgets per team.
Full dashboard UI included (53 components). This isn't vaporware.
See documentation →Free forever. Pro when you're ready.
7-day free trial on Pro — no credit card required.
Free
A complete, production-ready tool. No strings attached.
- 50% average savings on API costs
- Full local proxy — runs on your machine
- Rule-based routing — works offline, zero latency
- Local Ledger learning
- Works with any LLM provider
- Yours forever — MIT licensed, no lock-in
Break-even math: Pro pays for itself at $60/mo API spend. If you're spending $100+/mo, you'll save $20-50/mo after the subscription.
We never see your prompts.
Your data stays on your machine. We only see anonymized metadata for routing decisions.
What we collect
Anonymized metadata only
What we NEVER collect
Zero access to your content
Verify it yourself
See exactly what gets sent
relayplane-proxy --auditThe TelemetryEvent interface shows exactly what's collected. Nothing else.
Common questions
Technical
What exactly does the Swarm learn? Is my data safe?
The Swarm only sees anonymized metadata: task type, token count, model used, success/fail. Never your prompts, code, or outputs. Think of it like Waze—everyone's anonymous driving data makes traffic predictions better for everyone. Your actual prompts never leave your machine.
What if the cheap model returns garbage?
RelayPlane automatically retries with a better model. You pay for both calls, but that's still cheaper than always using Opus. The Swarm learns from failures so routing improves over time.
How much latency does this add?
Local proxy: <5ms. Swarm API call: 50-100ms. For a 2-5 second LLM call, this is negligible. If latency matters more than cost, configure more aggressive model selection.
What if the Swarm API goes down?
Proxy falls back to static rules automatically. Your agent keeps working. This is baked into the architecture—we assume network calls can fail.
Trust & Business
Can I audit exactly what's being sent?
Yes. Run `relayplane-proxy --audit` to see every payload before it's sent. Or read the MIT-licensed source code on GitHub.
What if you shut down?
The local proxy works forever—it's MIT licensed software on your machine. Only the Swarm API would stop. You'd keep ~50% savings on static rules.
Will this break my agent?
No. If RelayPlane can't route, it passes through to your default model. Worst case: you pay what you would have paid anyway.
How do I know I'm actually saving money?
Run `relayplane stats` or check the cloud dashboard. We show you exactly how much you've saved vs. what you would have spent.
Built by a real person.
Matt Turley
Solo Founder · 20 years in software
I was spending over $200/month on LLM API credits running OpenClaw. RelayPlane cut that by 60%.
This is a real product from a real person, not a VC-funded growth hack. I've been independent for 16 years and I'll be around to fix bugs and answer questions.