Open source

Prefer to run the gateway yourself? Start with ModelGate OSS.

An open-source, local-first LLM gateway for cost visibility, usage analytics, and basic heuristic security signals. Point your OpenAI or Anthropic client at it and every call is logged, priced and scored on your own machine — no ModelGate account, no telemetry. It’s the same idea as ModelGate Cloud, small enough to read end to end.

Open source · Apache 2.0 · Early v0.1.0
View on GitHub View v0.1.0 release
  • OpenAI Chat Completions & Responses
  • Anthropic Messages
  • Incremental streaming relay
  • Token & estimated cost tracking
  • Latency & error visibility
  • Repeated-request detection
  • Transparent heuristic security rules
  • Searchable local dashboard
  • Local SQLite storage
  • Prompts & responses not stored by default
  • No ModelGate account required
  • No ModelGate telemetry
Quick startDocker Compose
git clone https://github.com/razdgann/modelgate-oss.git
cd modelgate-oss
cp .env.example .env
docker compose up --build
The ModelGate OSS local dashboard: a searchable request ledger with tokens, latency, estimated cost and a waste score per call.
The local ModelGate OSS dashboard, shown with deterministic demo data — not production traffic.

ModelGate OSS

Runs on your machine

  • Local gateway
  • Local observability
  • Estimated costs
  • Basic heuristic signals
  • Local storage & dashboard

ModelGate Cloud

Managed, and a step further

  • Managed infrastructure
  • Continuous optimization
  • Advanced runtime protection
  • Shared team analytics
  • Longer retention
  • Commercial optimization recommendations

ModelGate OSS v0.1.0 is an early release and is not yet recommended for critical production workloads without your own validation.