I Built a Self-Hosted LLM Observability Tool for AI Applications (Logmera)

Source: Dev.to

The Problem: Lost Visibility in AI Applications

When building AI applications, you quickly lose visibility into what the system is doing. Common questions arise:

• What prompts were sent to the model?
• What responses came back?
• How long did the request take?
• Which model handled the request?
• Why did a request fail?

Developers often start by logging to the console, but this becomes messy and unmanageable in production.

Introducing Logmera

Logmera is a self‑hosted observability tool for AI/LLM applications. Instead of printing logs to the console, it stores:

• prompts
• responses
• model name
• latency
• request status

in a PostgreSQL database and presents them in a simple web dashboard.

Why Self‑Hosted?

Many LLM observability tools send data to external cloud services, which can raise concerns about:

• privacy
• compliance
• data ownership

Logmera runs entirely on your own infrastructure, keeping all logs inside your PostgreSQL database.

Architecture

Your AI Application
        │
        ▼
Logmera Python SDK
        │
        ▼
Logmera Server (FastAPI)
        │
        ▼
PostgreSQL Database
        │
        ▼
Dashboard

Quick Start (≈2 minutes)

Install the SDK

pip install logmera

Run the Server

Logmera requires a PostgreSQL database. Start the server with the connection URL:

logmera --db-url "postgresql://username:password@localhost:5432/database"

The server will be available at:

Log a Request from Python

import logmera

logmera.log(
    project_id="chatbot",
    prompt="Hello",
    response="Hi there",
    model="gpt-4o",
    latency_ms=120,
    status="success"
)

After executing the code, the request appears in the dashboard.

Dashboard Features

• Browse logs
• Search prompts
• Filter by project or model
• Track latency
• Inspect full responses

These capabilities make debugging AI systems much easier.

REST API

Logs can be sent from any language via the exposed REST endpoint.

curl -X POST http://127.0.0.1:8000/logs \
  -H "Content-Type: application/json" \
  -d '{
        "project_id":"demo",
        "prompt":"Hello",
        "response":"Hi",
        "model":"gpt-4o",
        "latency_ms":95,
        "status":"success"
      }'

Typical Use Cases

• AI SaaS applications
• Chatbots
• Retrieval‑augmented generation (RAG) systems
• AI agents
• Automation tools powered by LLMs

Logmera provides simple, real‑time visibility into what your AI system is doing.

Resources

• PyPI:
• GitHub:

If you’re building AI applications, feel free to try Logmera and share your feedback.