Install SentriNode — pick your stack

Choose your platform & installation method

For Python apps calling OpenAI or Anthropic. Two lines and every call is traced — cost, tokens, latency.

shell

pip install sentrinode-llm

Pass your tenant + key straight into instrument() — no shell environment variables to fuss with, works on any OS.

app.py

import sentrinode_llm sentrinode_llm.instrument(tenant="your-tenant", api_key="your-api-key") # now use openai / anthropic as normal — every call is tracked

For production, omit the arguments and set SENTRINODE_TENANT + SENTRINODE_API_KEY as environment variables instead.

A native Node SDK is in the works. coming soon

Until then, Node and Next.js apps can send telemetry today over OpenTelemetry — point any OTLP exporter at the ingest endpoint with your tenant headers. See the cURL / OTLP tab for the endpoint and headers.

Any language. Point an OpenTelemetry/HTTP exporter at the ingest endpoint with your tenant headers — no language-specific SDK required.

endpoint

POST https://api.sentrinode.com/v1/otlp/traces Headers: X-Tenant-Id: your-tenant X-SentriNode-Key: your-api-key Content-Type: application/json Body: standard OTLP/HTTP JSON spans (use gen_ai.* attributes for LLM cost)

Run the full SentriNode stack on your own server (FastAPI ingest + API + Neo4j + Redis) with Docker Compose.

shell

git clone https://github.com/rg309/sentrinode cd sentrinode/sentrinode cp .env.example .env # fill in your Supabase values docker compose -f docker-compose.hetzner.yml up -d --build

You also need a Supabase project (for auth + the database) and to apply the SQL migrations first. Full step-by-step: self-host guide →