How it works.
You ask a question. Your AI agent calls the LogNorth API. You get an answer.
You:
"What's breaking in production?"
Agent:
Found 3 errors in the last hour:
| Time | Message | Path |
|---|---|---|
| 14:32 | Database connection timeout | POST /checkout |
| 14:28 | Redis connection refused | POST /cart |
| 14:15 | Database connection timeout | POST /checkout |
The database timeout is recurring. Want me to show the full trace?
You:
"Yes. And fix it."
What you can ask.
"What errors are happening in production?"
"Show me checkout errors from the last hour."
"What are the most common errors this week?"
"Find all events for trace abc-123."
"When did this error first appear?"
Works with your tools.
Setup in 2 minutes.
Create an agent key in Settings. Set two environment variables. Install the skill.
# Shell profile export LOGNORTH_URL="https://logs.yoursite.com" export LOGNORTH_API_KEY="lgn-agent-..." # Install the skill npx skills add karloscodes/lognorth-releases --skill lognorth
Then ask your AI assistant about your production errors.
Read-only. Your server.
The agent API is read-only. It can query events and issues but never modify anything. Your logs stay on your server. The AI calls your API directly.
Ask a question. Get an answer. Fix the bug.
Full AI agent docs →