BigHugger
GH Repository · Scale3-Labs

langtrace

Langtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more.. Integrate using Typescript, Python. 🚀💻📊

stars
1,231
30-day movement
starts with the next reading
Related entries
60
Connections
1
nodeTypeScriptopen-sourceaillmobservabilitytracingopen-telemetrytypescriptdatasetsagent-frameworkprompt-engineeringllm-frameworkopenaievaluationsdockergptlangchainllmops

Langtrace is an open-source, OpenTelemetry-based observability tool for LLM applications, offering real-time tracing, evaluations, and metrics for popular LLMs, LLM frameworks, and vector databases. It integrates via TypeScript or Python SDKs and is developed by Scale3 Labs under an AGPL-3.0 license.

Use it when you need standards-based OpenTelemetry tracing and evaluation metrics across your LLM stack without building instrumentation yourself.

Use it to

  • Trace LLM application calls end-to-end
  • Collect metrics for LLM frameworks and vector databases
  • Run evaluations on model outputs
  • Instrument apps from TypeScript or Python
  • Export telemetry via OpenTelemetry

For Developers and LLMOps teams building LLM applications

Role
agent-framework
Language
TypeScript
Licence
AGPL-3.0
Forks
127
Open issues
1
Last push
2025-11-17
Latest release
1.0.0 · 2024-03-31
topicsobservabilitytracingopen-telemetryllmevaluationsllmops