# Fairvisor

Open-source edge enforcement engine for API rate limiting, LLM cost control, and agentic loop protection.

URL: https://fairvisor.com/

---


 Open source · MPL 2.0 Policy and spend control at the edge. Drop-in LLM endpoint. No SDK code changes. Run the edge (OSS) See how it works Open source · MPL 2.0 · Self-hostable < 70 µs enforcement overhead  ·  195k RPS Kong · Envoy · Nginx · Traefik Git-versioned policy Core enforcement primitives for API governance. Rate limits, budgets, and enforcement policies — as config, not code. Works for any API.
Unlike simple per-route rate limiting, Fairvisor enforces versioned, cost-aware, multi-tenant policies at the edge. Rate Limits & Quotas Per route, per key, per tenant — from JWT claims or headers.
One policy, enforced consistently at the edge.
Budgets Cost-aware spend caps per key, team, or endpoint.
Throttle or cut off traffic when real usage crosses defined thresholds.
Noisy Neighbor Isolation One tenant cannot degrade others.
Hard isolation via per-tenant limits and budgets.
Abuse Controls Bot and crawler detection (ASN, fingerprinting signals).
Edge enforcement only — not a WAF, no payload inspection.
Point your existing LLM clients at Fairvisor — change the base URL and API key format, nothing else. Token limits, cost budgets, and loop detection → Policy as code. Not a backend hack. Define policies in JSON, version in Git, validate in shadow mode, then promote with confidence.
Define Versioned policies Full version history and safe rollback. Policy changes are reviewed and deployed — not hidden in application code.
{ "selector": { "path_prefix": "/v1/chat/" }, "limit_keys": ["jwt:org_id"], "rules": [ { "limit": "pro-tier" }, { "budget": 500, "period": "1d", "unit": "USD" } ] } Test Shadow mode Limits are calculated but not enforced. See exactly which requests would be blocked before switching to hard enforcement.
fairvisor validate ./policies.json fairvisor test --dry-run # logs what would be enforced # on your real traffic Enforce Edge enforcement Sub-millisecond, in-process enforcement. If the control plane is unreachable, last-known policy remains active.
docker run -d fairvisor/edge \ --config ./policies.json \ --upstream http://your-api:8080 Policy-as-code via Git in v1 — SaaS adds review & approve UI and multi-environment deploy. For teams running APIs in production
Open-source edge. Production-ready SaaS control plane. The edge is free and runs standalone. The SaaS adds policy management, visibility, and team features.
Edge (open source, always free) Reverse proxy or decision service mode Sub-ms, in-memory enforcement Fails open or closed — configurable Prometheus metrics, Kubernetes-ready SaaS control plane — why teams upgrade Policy editor with validation Fleet management Analytics: top limited routes, tenants, abusive sources Alerts (Datadog, Sentry, PagerDuty, Prometheus) Audit exports for SOC 2 workflows RBAC and SSO (Enterprise) Fairvisor is not a WAF and not an API gateway replacement. It is a dedicated policy enforcement layer for API governance. Works with Kong / Envoy / Nginx / Traefik — see comparisons → Adopted when API enforcement becomes a business problem. Public APIs with paid tiers You enforce Free / Pro / Enterprise tiers.
Hard limits at the edge — not best-effort checks in code.
Partner integrations Each partner has its own contract.
Per-integration limits and kill switches enforced in real time.
Outgrown your API gateway's rate limiting High-volume APIs where per-request gateway pricing no longer makes sense.
Keep your gateway. Add a dedicated enforcement layer.
Predictable failure Deterministic enforcement: warn → throttle → reject.
No surprise overage at month end.
LLM spend control — no SDK changes Point your existing LLM clients at Fairvisor as a drop-in endpoint. Change the base URL and API key format — no application code changes. Policy and spend control apply transparently. See AI enforcement →
Multi-tenant SaaS One tenant's traffic spike shouldn't degrade service for others.
Hard per-tenant isolation enforced at the edge — not patched in application code.
What teams say "Fairvisor lets us keep latency promises to users without burning unnecessary compute. Efficiency became a quality metric, not a compromise." Max Usubyan CEO, thebutton.ai "Growth is healthy only when it's predictable. Fairvisor made our API expansion controllable — in both performance and cost." Sergey Shalaev CEO & Co-Founder, Solda.AI 5 minutes from zero to enforcement Start in shadow mode, validate policy behavior, then switch to hard enforcement.
Read the quickstart guide The edge engine is free and open source. See SaaS pricing →