llm-tracing

Python 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

AgentInsight Python SDK provides a Python client for the AgentInsight platform, supporting LLM application observability, tracing, evaluation, and prompt management.

An exporter of openclaw traces to langfuse using logs

A Streamlit-based AI assistant generates custom Streamlit app code from user-provided images or text using the Google Gemini model.

🤖 Build advanced AI agents with a collection of production-ready applications using modern frameworks for single and multi-agent systems.

Single-binary, MLflow-API-compatible experiment tracker with first-class LLM trace support. 143× faster cold start than MLflow.

Open-source, self-hostable AI cost & workflow observability. Find the prompt, customer, model, and workflow path behind every LLM cost spike — without a proxy.

Site Sleuth is a chatbot that assists users in efficiently using websites by analyzing and answering questions provided through a link.

Open-source evaluation and observability platform for AI agent applications.

Agent cognitive middleware — inspect, detect, and verify agent reasoning in real time. By LatticeAG.

Drop-in observability for LLM apps — quality scoring, hallucination detection, cost tracking and agent debugging

Open-source cryptographic audit trail for AI agents. Produces cryptographic receipts - SHA-256 hash-chained, tamper-evident, verifiable offline. Supports EU AI Act Article 12 traceability.

AgentGlass — a glass box for your AI agents. Capture, inspect, replay, and analyze every agent run (LLM observability & tracing). No SDK, no code changes.

LLM Tracker is a platform for analyzing and visualizing LLM usage and costs across your projects. It provides a simple interface to monitor your expenses and understand how your different models are being used.

The comprehensive list of LLM observability tools: 120 open-source and commercial platforms for AI tracing, monitoring, evaluation, analytics, cost, and security.

A lightweight, local-first observability proxy and dashboard designed to intercept, log, and trace LLM interactions. OpenInspector acts as a transparent middleman, offering full visibility into agentic workflows, tool executions, and latency metrics without requiring you to change a single line of your application code.

The official JavaScript/TypeScript client library for sending AI application observability data to the AgentInsight platform.

In this we implement opik llm evaluation metrics on medical data analyzer