Awesome Observability

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

SigNoz is an open-source, OpenTelemetry-native observability platform for your team and their AI agents. Get logs, metrics, and traces in one tool with features like APM, distributed tracing, log management, infra monitoring, etc. Combined with SigNoz MCP and a native AI teammate (in SigNoz Cloud) it helps you build more resilient apps.

Like Prometheus, but for logs.

Write scalable load tests in plain Python 🚗💨

A high-performance observability data pipeline.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

record and replay the web

GoReplay is an open-source tool for capturing and replaying live HTTP traffic into a test environment in order to continuously test your system with real data. It can be used to increase confidence in code deployments, configuration changes and infrastructure changes.

Daemon for easy but powerful stats aggregation

Zipkin is a distributed tracing system

:tropical_fish: Beats - Lightweight shippers for Elasticsearch & Logstash

AI Observability & Evaluation

Checkmate is an open-source, self-hosted tool designed to track and monitor server hardware, uptime, response times, and incidents in real-time with beautiful visualizations. Don't be shy, join here: https://discord.com/invite/NAb6H3UTjK :)

Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.

Prometheus Alertmanager

Open Source LLM Gateway 🦚

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

Connect Your Agents And Harnesses With Any Provider 🦚

The open-source observability database. One columnar engine for metrics, logs, and traces, on object storage.

Real-time monitoring of IT components and services, such as networks, servers, VMs, applications and the cloud.

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

A horizontally scalable, highly available, multi-tenant, long term Prometheus.

M3 monorepo - Distributed TSDB, Aggregator and Query Engine, Prometheus Sidecar, Graphite Compatible, Metrics Platform

Agenta is a workspace where you and your team build agents and automations.

Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.

AI observability platform for production LLM and agent systems.

WebGL visualization for displaying animated traffic graphs

Observe any stack, any service and any data, using any UI components you prefer, never missing any X factors and resolve them before they become real problems.

Distributed tracing without code changes. 🚀 Instantly monitor any application using OpenTelemetry and eBPF

OpenTelemetry Collector distribution with programmable pipelines

🚀 Realtime Monitoring solution for Node.js/Express.js apps, inspired by status.github.com, sponsored by https://dynobase.dev

In-memory dimensional time series database.

Vector is an on-host performance monitoring framework which exposes hand picked high resolution metrics to every engineer’s browser.

Laminar - open-source observability platform purpose-built for AI agents. YC S24.

Simple gRPC benchmarking and load testing tool

FlameScope is a visualization tool for exploring different time ranges as Flame Graphs.

OpenLIT is the open-source agent harness engineering platform: trace, evaluate, guard, and improve everything around the model in your AI agents, on OTEL.

A Kubernetes operator for running synthetic checks as pods. Works great with Prometheus!

Scouter is an open source APM (Application Performance Management) tool.

Automation-friendly framework for Continuous Testing by

Open source monitoring and visualization UI for the TICK stack

Simple Kubernetes real-time dashboard and management.

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. 🚀💻📊

Dev Tools for the Serverless World - Issues, PRs and ⭐️welcome!

ML powered analytics engine for outlier detection and root cause analysis.

Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time. Lightweight background daemon (<50MB RAM), SQLite storage, Material Design 3 dashboard. Zero telemetry.

DataBuff is an AI-native APM built on Opentelemetry，with multi-agent troubleshooting out of the box.

The pub/sub library for node backed by Redis, MongoDB, AMQP (RabbitMQ), ZeroMQ, MQTT (Mosquitto) or just plain node!

A programmable, observable and distributed job orchestration system.

A load generator in Go language