Torrix: Self-Hosted LLM Observability Without Postgres or Redis

Torrix is a self-hosted LLM observability tool designed for teams who want to see what their agents are doing in production without the overhead of Postgres, Redis, or complex infrastructure. It runs as a single Docker container backed by SQLite. The full install is:

curl -o docker-compose.yml https://raw.githubusercontent.com/torrix-ai/install/main/docker-compose.community.yml
docker compose up

No external dependencies. All data stays in a local SQLite file on your machine. After startup, open http://localhost:8088 and create an account.

Key Features

• LLM call logging via HTTP proxy or Python/Node.js SDK: tokens, cost, latency, full prompt and response traces, reasoning token capture.
• Provider support: OpenAI, Anthropic, Gemini, Groq, Mistral, Azure OpenAI, and any OpenAI API-compatible endpoint.
• Cost forecasting and hard budget caps
• PII masking
• Model routing rules
• Evals with golden runs and AI judge
• Prompt library with version history
• Run tags for filtering by environment
• MCP server so AI Assistants can query your own logs
• OTLP/HTTP ingestion for apps already using OpenTelemetry

SDK Usage Example (Python)

pip install torrix

import torrix
from openai import OpenAI
torrix.init(api_key="<your-torrix-api-key>", base_url="http://localhost:8088")
client = torrix.wrap(OpenAI(api_key="<your-openai-key>"))
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
    torrix_name="my-run",
)
print(response.choices[0].message.content)

The Node.js SDK is also available via npm install.

Licensing and Scaling

Community edition is free for one user with 7-day retention. Pro adds teams, RBAC, 30-day retention, API key management, full text search, and audit logs. SQLite doesn't scale to high write throughput; this is aimed at teams logging hundreds to low thousands of LLM calls per day, not millions.