Awesome Infra for AI › LLM Observability & Tracing

evilmartians/agent-prism

⭐ 393 TypeScript repository created 2025-07-22

AgentPrism provides a set of React components designed for visualizing the execution traces of AI agents. It addresses the challenge of understanding agent behavior by transforming raw trace data, particularly from OpenTelemetry and Langfuse, into intuitive, hierarchical visual diagrams. The library allows developers to observe LLM calls, tool executions, and agent workflows in a structured timeline, which is crucial for debugging and optimizing AI agent performance. It offers a `TraceViewer` component for a complete visualization interface, including a trace list, tree view, and details panel, and also allows for custom layouts using individual components like `TraceList`, `TreeView`, and `DetailsView`. AgentPrism includes data adapters to normalize various trace formats, supporting OpenTelemetry GenAI, OpenInference, and standard OTEL attributes. The project is specifically built for the operational phase of AI, focusing on observability and debugging post-deployment, rather than model training or general-purpose data visualization. It supports React 19+, Tailwind CSS 3, and TypeScript environments.

https://github.com/evilmartians/agent-prism

ai-agentsai-monitoringcomponent-librarydeveloper-toolsdistributed-tracinggenerative-ailangchainllmllm-observabilitymonitoringobservabilityopen-sourceopentelemetryreactreact-componentstailwindcsstrace-visualizationtracingtypescriptui-components

Also in LLM Observability & Tracing

langfuse/langfuse

Langfuse is an open-source LLM engineering platform for developing, monitoring, evaluating, and debugging AI applications, offering observability, prompt management, and evaluation capabilities.

comet-ml/opik

Opik is an open-source platform for comprehensive observability, evaluation, and optimization of LLM applications, RAG systems, and agentic workflows.

raga-ai-hub/RagaAI-Catalyst

RagaAI Catalyst is a Python SDK for comprehensive observability, monitoring, and evaluation of AI agents and LLM applications, offering tracing, debugging, and advanced analytics.

Arize-ai/phoenix

Phoenix is an open-source AI observability platform for LLM application experimentation, evaluation, and troubleshooting, providing tracing, evaluation, dataset management, prompt management, and a...

VoltAgent/voltagent

VoltAgent is an end-to-end AI Agent Engineering Platform offering an open-source TypeScript framework for building intelligent agents and a VoltOps Console for observability, automation, deployment...

traceloop/openllmetry

OpenLLMetry provides open-source observability for LLM applications by extending OpenTelemetry to capture traces and metrics from LLM providers, vector databases, and AI frameworks.

Helicone/helicone

Helicone is an open-source LLM observability platform and AI gateway that provides monitoring, evaluation, prompt management, and intelligent routing for large language models.

Agenta-AI/agenta

Agenta is an open-source LLMOps platform designed to accelerate the development of reliable LLM applications, offering integrated prompt management, evaluation, and observability features.