
telemetry.dev精选
LLM observability for AI agents
telemetry.dev shows each run of your AI agent as one trace. Each model call and tool call is a span with its duration, tokens, cost, and error. Prompts and evals use the same traces: change a prompt without a deploy, then run it on a dataset and compare the scores with production. Alerts tell you about errors, cost spikes, and agent loops. Connect with our TypeScript or Python SDK, or with the OpenTelemetry exporter that you already use.
2026-10-31 同榜
801
SpecsightProduct observability for teams shipping fast with AI▲ 30602
SKIVoice-first coding harness ▲ 28804
BackenlyThe autonomous backend for AI coding agents▲ 15105
WinnerAdSpyTurn competitor ad insights into winning app campaigns▲ 14606
LumaFold: Screen LightMakeup Mirror & Color Effects for iPhone Duo▲ 14207
Secret KeyLet your family unlock your passwords if you can't▲ 10008
Knuckleboptap your palm rest to control your Mac▲ 9809
GitHub Copilot FusionGitHub's AI coding agent that picks and combines models▲ 98