Foglamp - Observability for AI agents<br>svg:first-child]:pl-2 has-[>svg:last-child]:pr-2">svg:first-child]:pl-2 has-[>svg:last-child]:pr-2" href="/login">Start monitoring

Ship AI agents you can actually see<br>See the cost, latency, and quality of every LLM call. Catch bad output before your users do.<br>svg:first-child]:pl-2.5 has-[>svg:last-child]:pr-2.5 text-base" href="/login">Start free<br>Copy agent prompt

| Tailor made for

“Caught a 10× cost regression 3 days after shipping. Foglamp paid for itself in week one.”<br>GGustavo Fior· Co-founder @ Foglamp yes, it's me :)<br>Week 1Ships clean.<br>Week 3Costs doubled, answers worse.<br>ThenCustomers start complaining.<br>Dana#support2m<br>the assistant just quoted a refund window we killed in March 😤

+1 (415) 555-0148Customer6m<br>is this a bot? it gave me an order number that doesn't exist

@jordanbuilds12.4k followers14m<br>@acme your “AI support” confidently invented a tracking link. yikes.

maracommunity21m<br>anyone else getting totally wrong answers from the bot today??

One SDK in. Everything out.<br>Instrument once. Get cost, traces, evals, alerts, and per-agent spend on every call.

SDK

Two lines instruments every generateText / streamText call.<br>import { foglamp } from "foglamp"const fog = foglamp()

Agents

Per-agent spans, latency, and spend - with the full call flow.<br>orchestratorCopy agent prompt