Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Save ~$47/mo on a typical $100/mo OpenClaw spend. Local proxy routes simple tasks to cheaper models automatically.
Save ~$47/mo on a typical $100/mo OpenClaw spend. Local proxy routes simple tasks to cheaper models automatically.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
OpenRouter routes. RelayPlane observes, governs, and learns. Agent ops for OpenClaw power users. Your agents make hundreds of API calls per session โ RelayPlane gives you visibility, cost control, and governance over all of them.
RelayPlane is an optional optimization layer that sits in your agent's request pipeline. It routes simple tasks to cheaper models, enforces budgets, and logs everything โ with automatic fallback to direct provider calls if anything goes wrong. Key principle: RelayPlane is never a dependency. If the proxy dies, your agents keep working. Zero downtime, guaranteed.
npm install -g @relayplane/proxy@latest
# 1. Start the proxy (runs on localhost:4100 by default) relayplane-proxy # 2. Add to your openclaw.json: # { "relayplane": { "enabled": true } } # 3. That's it. OpenClaw routes through RelayPlane when healthy, # falls back to direct provider calls automatically.
Never do this: # โ WRONG โ hijacks ALL traffic, breaks OpenClaw if proxy dies export ANTHROPIC_BASE_URL=http://localhost:4100 Instead, use the config approach: // โ RIGHT โ openclaw.json { "relayplane": { "enabled": true } } The config approach uses a circuit breaker โ if the proxy is down, traffic goes direct. The BASE_URL approach has no fallback and will take down your entire system.
Agent โ OpenClaw Gateway โ Circuit Breaker โ RelayPlane Proxy โ Provider โ (on failure) Direct to Provider Circuit breaker: 3 consecutive failures โ proxy bypassed for 30s Auto-recovery: Health probes detect when proxy comes back Process management: Gateway can spawn/manage the proxy automatically
Minimal (everything else has defaults): { "relayplane": { "enabled": true } } Full options: { "relayplane": { "enabled": true, "proxyUrl": "http://127.0.0.1:4100", "autoStart": true, "circuitBreaker": { "failureThreshold": 3, "resetTimeoutMs": 30000, "requestTimeoutMs": 3000 } } }
CommandDescriptionrelayplane-proxyStart the proxy serverrelayplane-proxy statsView usage and cost breakdownrelayplane-proxy --port 8080Custom portrelayplane-proxy --offlineNo telemetryrelayplane-proxy --helpShow all options
import { RelayPlaneMiddleware, resolveConfig } from '@relayplane/proxy'; const config = resolveConfig({ enabled: true }); const middleware = new RelayPlaneMiddleware(config); // Route a request โ tries proxy, falls back to direct const response = await middleware.route(request, directSend); // Check status const status = middleware.getStatus(); console.log(middleware.formatStatus());
import { createSandboxedProxyServer } from '@relayplane/proxy'; const { server, middleware } = createSandboxedProxyServer({ enableLearning: true, // Enable pattern detection enforcePolicies: true, // Enforce budget/model policies relayplane: { enabled: true }, // Circuit breaker wrapping }); await server.start(); // All three pillars active: Observes + Governs + Learns // Circuit breaker protects against proxy failures
Three Pillars โ All Integrated: Observes (Learning Ledger) โ every run captured, full decision explainability Governs (Policy Engine) โ budget caps, model allowlists, approval gates Learns (Learning Engine) โ pattern detection, cost suggestions, rule management Sandbox Architecture (v1.3.0+): Circuit breaker โ automatic failover, no more system outages Process manager โ proxy runs as managed child process Health probes โ active recovery detection Stats & observability โ p50/p95/p99 latencies, request counts, circuit state Learning Engine Endpoints (v1.4.0): GET /v1/analytics/summary โ analytics with date range POST /v1/analytics/analyze โ detect patterns, anomalies, generate suggestions GET /v1/suggestions โ list pending suggestions POST /v1/suggestions/:id/approve / reject โ suggestion workflow GET /v1/rules โ active rules GET /v1/rules/:id/effectiveness โ is this rule helping?
Your prompts stay local โ never sent to RelayPlane servers Anonymous telemetry โ only token counts, latency, model used Opt-out anytime โ relayplane-proxy telemetry off Fully offline mode โ relayplane-proxy --offline
Docs: https://relayplane.com/docs GitHub: https://github.com/RelayPlane/proxy npm: https://www.npmjs.com/package/@relayplane/proxy
Long-tail utilities that do not fit the current primary taxonomy cleanly.
Largest current source with strong distribution and engagement signals.