Self-host Superlog for AI-triaged logs
Superlog turns OTLP traces, logs and metrics into incidents an agent triages. Run the self hosted stack on your own VPS, and know the real footprint first.
#observability
Filtering by topic #observability · clear
Self-host Langfuse to trace your AI agents
Run Langfuse on your own VPS: the real resource floor, pinned image tags, TLS, ClickHouse retention before it fills the disk, and backups that work.
Claude Code spend tracking tools compared
Claude Code spend trackers answer different questions. Compare local log parsers against the built-in usage screens and your own OpenTelemetry stack.
Self-host agent-console for coding agents
Run the agent-console hub on a VPS so a laptop and every agent box report Claude Code and Codex token use to one place, reached over an SSH tunnel.
Numbat: watch what your AI agents do
Perplexity open sourced Numbat, an endpoint monitor that records what AI coding agents really do on your servers. What it sees, and what it cannot stop.
Self-hosted error tracking: Sentry alternatives
Sentry self-hosted wants 16 GB RAM. GlitchTip runs in 512 MB. Compare RAM, disk growth, container count and upgrade pain before you pick one.
Self-hosted evals for AI agents
Build an eval loop you own: golden cases from real traces, cheap deterministic checks first, an LLM judge second, and a pass rate you track per commit.