{"repo":"traccia-ai/traccia-py","free":true,"listed":false,"github":"https://github.com/traccia-ai/traccia-py","clone":"git clone https://github.com/traccia-ai/traccia-py.git","description":"OpenTelemetry-native SDK for AI agent observability, tracing, evaluation, debugging, governance, and runtime policy enforcement. Framework-agnostic and built for OpenAI Agents, LangGraph, CrewAI, and LLM applications in production.","language":"Python","stars":100,"topics":["agent","agent-governance","agent-monitoring","agent-optimization","agent-policies","agentic-ai","observability","agent-governance-autonomous-systems","agent-monitoring-policy-engine","ai"],"license":"Apache-2.0","category":"analytics","readme_excerpt":"Traccia OpenTelemetry-based observability, distributed tracing, evaluation, governance, and compliance for AI agents and LLM applications Traccia is a production-ready Python SDK for observability, distributed tracing, evaluation, governance, and compliance across AI agents, LLM applications, agentic workflows, and multi-agent systems. Built on OpenTelemetry standards, Traccia provides automatic instrumentation, token and cost tracking, offline evaluation, guardrail detection, AI governance evidence, and OTLP-compatible exports for modern AI applications. Traccia is available on PyPI. Features - Automatic Instrumentation : Auto-patch OpenAI, Anthropic, Gemini (google-genai), requests, and HTTP libraries - Framework Integrations : Support for LangChain, CrewAI, and OpenAI Agents SDK - LLM-Aware Tracing : Track tokens, costs, prompts, completions, and latency automatically - OpenTelemetry Metrics : Emit OTEL-compliant metrics for accurate token and cost tracking independent of sampling - Zero-Configuration Setup : Simple init() call with automatic configuration discovery - Decorator-Based Tracing : Trace any function with the @observe decorator - Multiple Exporters : OTLP-compatible export to Grafana Tempo, Jaeger, Zipkin, SigNoz, Console, or File - Production-Ready Architecture : Rate limiting, error handling, configuration validation, and reliable flushing - Guardrail Detection : Passive detection of AI safety controls, provider-native safeguards, and custom guardrails - AI G","default_branch":null,"files":null,"tree":[],"storefront":"/r/traccia-ai","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/traccia-ai/traccia-py/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}