AI gateway: smart routing, budget control, PII guard, semantic cache, single static binary.
979
Deploying AI models to production brings critical operational challenges such as unpredictable costs, data privacy risks, and API outages. ILTER is an independent gateway that sits between your application and AI providers, transforming your entire AI traffic into a secure, optimized, and fully controlled infrastructure without requiring any architectural changes in your code.
Ships as a zero-setup, single static binary — this image is a scratch-based build under 20MB.
Admin key + a provider key are enough to boot straight into serve — no ilter init step needed. The SQLite DB is created on first start, and the provider whose ILTER_PROVIDER_<NAME>_API_KEY is set is enabled automatically.
docker run -d \
-p 8181:8181 -p 9191:9191 -p 9192:9192 \
-v $(pwd)/data:/app/data \
-e ILTER_ADMIN_API_KEY=<your-own-random-secret> \
-e ILTER_PROVIDER_OPENAI_API_KEY=sk-... \
ykocaman/ilter:latest
/metrics)Without ILTER_ADMIN_API_KEY and a provider key both set, serve refuses to start and exits with a message telling you to set both.
OpenAI, Anthropic, Google Gemini, DeepSeek, OpenRouter, Ollama, Qwen (Alibaba), OpenCode, and a built-in Mock provider for local testing.
Zero configuration by default — compiled defaults + ILTER_* env vars. Runtime and per-key overrides (PII toggles, providers, routing strategies, budgets, rate limits) are available via the embedded dashboard or the Admin API.
Content type
Image
Digest
sha256:f373959fa…
Size
10.2 MB
Last updated
about 2 months ago
docker pull ykocaman/ilter