Traccia LogoTraccia Logo Dark
About TracciaPricingGovernanceSecurityBlogDocs
Book a demoStart free
Overview
Quickstart
Installation
Agents
Traces
Spans
OpenTelemetry
@observe()
Agent Identity
Auto-Instrumentation
Exporters
Metrics
Pricing & Costs
Guardrail Detection
Governance
Prompts
Evaluate
Advanced
LangChain
Claude Code
Cursor
GitHub Copilot
CrewAI
OpenAI Agents SDK
Gemini SDK
Overview
OpenAI SDK
Anthropic SDK
Gemini SDK
LangChain
LiteLLM
Vercel AI SDK
LlamaIndex
CrewAI
OpenAI Agents SDK
n8n
HTTP
Getting Started
OTLP Ingestion
Dashboard
Compliance Hub
Policies
Guardrail Posture
Prompts
Prompt Playground
Datasets
Scorers
Experiments
Teams
Costs
Traces
EU AI Act Compliance
HIPAA Controls for AI Agents
Cap Refunds And Purchases
Approve A Refund Or Purchase
Stop A Dangerous Tool
Multi-Agent Tracing
Parallel Runs
Local Jaeger Setup
Grafana Tempo Setup
Cost Optimization
Run Experiments From Code
Run Evals In CI
Compare Two Experiments
Troubleshooting
Python SDK API
TypeScript SDK API
CLI Commands
Configuration
Events
Errors
Release Notes
FAQ
Coupon Codes

SDK

Instrument your agents with the Traccia SDK — decorators, auto-instrumentation, exporters, metrics, cost tracking, prompts, and evaluate().

SDK Quickstart

Get started with Traccia SDK in under 5 minutes.

Installation

Install the Traccia SDK for Python or TypeScript (Node.js).

@observe() Decorator

Instrument your functions with the @observe() decorator.

Agent identity

How agent and environment names appear when sending traces to the Traccia platform.

Auto-Instrumentation

Automatically trace LLM calls and popular libraries.

Exporters

Configure where your traces are exported.

Metrics

Understand the metrics emitted by the Traccia Python SDK and how to use them in Prometheus and Grafana.

Pricing & Costs

How the SDK calculates LLM costs locally, how to keep your pricing snapshot fresh, and how SDK costs relate to platform-recomputed costs.

Guardrail Detection

Passively detect, classify, and audit guardrails in your agent traces — zero runtime enforcement, no changes to existing code.

Governance in the SDK

Observe vs govern, trace evidence, and runtime policy enforcement.

Prompts in the SDK

Load versioned prompts at runtime with cache, fallback, and span identity.

Evaluate in the SDK

Run a task and scorers over a dataset from Python or TypeScript. Save an experiment by default, or keep the loop local.

Advanced SDK Topics

Manual spans, sampling, rate limiting, and advanced configuration.

© 2026 Traccia.