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.

Write scalable load tests in plain Python 🚗💨

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

Zipkin is a distributed tracing system

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 🦚

Connect Your Agents And Harnesses With Any Provider 🦚

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

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.

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.

OpenTelemetry Collector distribution with programmable pipelines

In-memory dimensional time series database.

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

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.

A lightweight schema-on-read analytics in a single binary

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

the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours

Agent and LLM API performance monitoring via network packet probe. Measures performance of OpenClaw, Claude, Codex, DeepAgents and more — deployed on the provider side, no SDK changes required.

Realistic synthetic events for testing, demos, and pipelines — streamed live or generated in bulk

Observability for AI coding assistants — cost tracking, efficiency scoring, and anti-pattern detection for Claude Code, Cursor, Copilot, and more. Local-first; New Relic optional.

Unified observability for logs, metrics and traces — low overhead instrumentation (Rust, Unreal Engine 5), OTLP ingestion, SQL analytics on DataFusion over Parquet, presentation through notebooks, Grafana and Python. Self-hosted.

Lightweight cost observability for every API call in your stack. Track LLM tokens, database ops, and external services from your terminal.

Lightweight self-hosted telemetry: errors, events, sessions, and a dashboard. Fastify API, Next.js UI, PostgreSQL, @telemetry-tracker/* SDKs.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit prompts.

Generate the complete reliability stack from a service spec in 5 minutes. Dashboards, alerts, SLOs, PagerDuty - zero toil.

Lightweight self hosted error tracking for indie devs and startup teams. Sentry SDK compatible. 2-container. Installation within 15s.

Weckr SDKs and Claude Skills: TypeScript, Python, MCP server, and an installable Claude Code plugin. AI cost and margin intelligence for SaaS, per user, per feature, per LLM call.

Local-first observability dashboard for AI agents. MCP-native. Look at every span your agents emit.

Local-first DevTools for AI calls. See every LLM call your app makes: prompt, cost, tokens, latency, tool calls.

Chat-driven Prometheus visualization with one-click Grafana export. Self-hosted, single image, bring your own LLM.

Privacy-first endpoint health for Node, Go, and OpenTelemetry services.