Foglamp
Tracks cost, latency, and quality of every LLM call, providing dashboards for requests, errors, latency, and evals.
Foglamp is an observability platform for AI agents that tracks the cost, latency, and quality of every LLM call, helping teams catch bad output before users do. It targets developers, data teams, and operations teams at companies of all sizes, from startups to enterprises. The platform is positioned as a missing observability layer, with a one-prompt setup that integrates with coding agents like Claude Code or Codex, and delivers a dashboard for monitoring requests, errors, latency, and evals.
Key features
- Track cost per LLM call
- Monitor latency percentiles
- Evaluate output quality
- Alert on errors
- Trace agent sessions
- View usage by model
- Breakdown by agent and workflow
- Customer-level usage insights
- No social media activity within the last 30 days
GTM channels
- API
- Docs
ICP
- Software developers
- Engineering teams
- DevOps sre teams