Relay is the orchestration console for AI agents in production. Route, observe, and recover every run from one surface.
NO CREDIT CARD · DEPLOY ON YOUR OWN INFRA
Four primitives cover the full lifecycle of a production agent run. Compose them, don't bolt them on.
Route every request by capability, cost, and latency. Cache hits skip the expensive path automatically.
Every tool call, token, and decision is a first-class trace. Drill from a failed run to its root cause.
Timeouts retry with backoff, failed tools degrade to fallbacks, and sessions resume from checkpoint.
Relay wraps your existing agent behind a thin config layer.
# relay.yaml — start with defaults, tune as you grow session: budget: $5.00 # hard cap, enforced pre-request resume: true # checkpoint on interrupt routing: default: deepseek-v4 fallback: [ deepseek-v3, gpt-oss ] cache: read # reuse prior turns tools: timeout: 30s retry: 2 degrade: true telemetry: traces: true export: ./relay-runs.jsonl
Deploy in minutes, tune in days, trust from the first run.
Get started free