https://observability.kymatalabs.com The living index of LLM & AI observability tooling — tracing, monitoring, online evaluation, agent observability, and ML-drift detection. https://observability.kymatalabs.com/p/langfuse-langfuse/langfuse/langfuse🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 https://observability.kymatalabs.com/p/comet-ml-opik/comet-ml/opikDebug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards. https://observability.kymatalabs.com/p/arize-ai-phoenix/Arize-ai/phoenixAI Observability & Evaluation https://observability.kymatalabs.com/p/traceloop-openllmetry/traceloop/openllmetryOpen-source observability for your GenAI or LLM application, based on OpenTelemetry https://observability.kymatalabs.com/p/helicone-helicone/Helicone/helicone🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓 https://observability.kymatalabs.com/p/pydantic-logfire/pydantic/logfireAI observability platform for production LLM and agent systems. https://observability.kymatalabs.com/p/agenta-ai-agenta/Agenta-AI/agentaThe open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place. https://observability.kymatalabs.com/p/latitude-dev-latitude-llm/latitude-dev/latitude-llmLatitude is the open-source ai monitoring platform. https://observability.kymatalabs.com/p/truera-trulens/truera/trulensEvaluation and Tracking for LLM Experiments and AI Agents https://observability.kymatalabs.com/p/lmnr-ai-lmnr/lmnr-ai/lmnrLaminar - open-source observability platform purpose-built for AI agents. YC S24. https://observability.kymatalabs.com/p/openlit-openlit/openlit/openlitOpen source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs. https://observability.kymatalabs.com/p/evidentlyai-evidently/evidentlyai/evidentlyEvidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics. https://observability.kymatalabs.com/p/liaohch3-claude-tap/liaohch3/claude-tapIntercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer. https://observability.kymatalabs.com/p/javis603-token-monitor/Javis603/token-monitorReal-time token, cost, and AI limits widget with multi-device sync for Claude Code, Codex, OpenCode, Hermes, OpenClaw, Cursor, Antigravity and more. | 为 AI Tools 打造的即时Token、成本与限额监控桌面组件，支持多设备同步 https://observability.kymatalabs.com/p/cvs-health-uqlm/cvs-health/uqlmUQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection https://observability.kymatalabs.com/p/judgmentlabs-judgeval/JudgmentLabs/judgevalThe Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring. https://observability.kymatalabs.com/p/simple10-agents-observe/simple10/agents-observeReal-time observability of claude code sessions & multi-agents. https://observability.kymatalabs.com/p/traceroot-ai-traceroot/traceroot-ai/tracerootTraceRoot - open-source observability and self-healing layer for AI agents. YC S25 https://observability.kymatalabs.com/p/vasihemanth-tokentelemetry/VasiHemanth/tokentelemetryToken telemetry dashboard for AI autonomous and coding agents — tracks tokens, sessions, tool calls & reasoning across Hermes agent, Claude Code, Antigravity CLI, Codex & more. 100% local. https://observability.kymatalabs.com/p/rajudandigam-agent-inspect/rajudandigam/agent-inspectLocal execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns manual steps, tool calls, LLM calls, structured logs, failures, durations, and run metadata into readable execution trees you can inspect from the terminal. I https://observability.kymatalabs.com/p/andreisirbu91-lab-mcpspend/andreisirbu91-lab/MCPSpendReal-time cost observability for Model Context Protocol (MCP) tool calls. Wraps any MCP server, attributes spend per tool/project/customer. Free tier 25K calls/mo. EU-hosted https://observability.kymatalabs.com/p/agentops-ai-agentops/AgentOps-AI/agentopsPython SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI https://observability.kymatalabs.com/p/traceloop-openllmetry-js/traceloop/openllmetry-jsSister project to OpenLLMetry, but in Typescript. Open-source observability for your LLM application, based on OpenTelemetry https://observability.kymatalabs.com/p/rhesis-ai-rhesis/rhesis-ai/rhesisThe testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. https://observability.kymatalabs.com/p/stainlu-hermes-labyrinth/stainlu/hermes-labyrinthRead-only observability plugin for Hermes Agent: journeys, crossings, guideposts, and reports. https://observability.kymatalabs.com/p/raga-ai-hub-ragaai-catalyst/raga-ai-hub/RagaAI-CatalystPython SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view https://observability.kymatalabs.com/p/pezzolabs-pezzo/pezzolabs/pezzo🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more. https://observability.kymatalabs.com/p/chirpz-ai-pandaprobe/chirpz-ai/pandaprobeopen source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more. https://observability.kymatalabs.com/p/vstorm-co-agentcanvas/vstorm-co/agentcanvasVisualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost. https://observability.kymatalabs.com/p/msfirebird-claw-lens/msfirebird/claw-lensOpen-source observability dashboard for OpenClaw daemons — cost analyti cs, live monitor ing, and de bugging tools, all running on your own machine.