Awesome Opentelemetry

Open Source LLM Gateway 🦚

Connect Your Agents And Harnesses With Any Provider 🦚

Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

Web UI for Jaeger

🔭 Tracetest - Build integration and end-to-end tests in minutes, instead of days, using OpenTelemetry and trace-based testing.

See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.

World's first fully integrated and fully Automated Kubernetes management and orchestration solution

OpenTelemetry traces from Playwright tests - with propagation, OTLP export, and a viewer that pairs screenshots with backend spans

Single-binary observability platform. Ingest OTLP, store as Parquet, query with DuckDB.

OpenTelemetry SpanExporter for the Vercel AI SDK → Voight. Drop-in observability

Local-first AI reasoning observability for Swift: record, diff, attest, and CI-gate agent execution paths. Complements OpenTelemetry and tools like LangSmith — does not replace them.

OpenTelemetry instrumentation for viem, the Coinbase CDP SDK, x402 and MPP: trace the transactions and payments your AI agents and services send, keyed by tx hash.

Self-hostable log storage and search. Point any OTLP-compatible shipper at one HTTP endpoint, and get a fast, searchable, live-tailing view of your logs — backed by ClickHouse, on your own box.

Self-hosted, OpenTelemetry-native log dashboard for .NET: live-tail logs, correlate traces & metrics, and alert on breaches via Slack/Telegram/webhook/email — all over plain OTLP. A self-hosted alternative to Seq or Datadog Logs.