genai-otel-instrument 1.2.0

Comprehensive OpenTelemetry auto-instrumentation for LLM/GenAI applications

TraceVerde

The most comprehensive OpenTelemetry auto-instrumentation library for LLM/GenAI applications

Trace from OpenTelemetry traces. Verde meaning green - for sustainable, transparent AI observability.

Documentation | Examples | Discord | PyPI

---

Get Started in 30 Seconds

pip install genai-otel-instrument

import genai_otel
genai_otel.instrument()

# Your existing code works unchanged - traces, metrics, and costs are captured automatically
import openai
client = openai.OpenAI()
response = client.chat.completions.create(model="gpt-4o-mini", messages=[{"role": "user", "content": "Hello!"}])

That's it. No wrappers, no decorators, no config files. Every LLM call, database query, and agent interaction is automatically traced with full cost breakdown.

Why TraceVerde?

Feature	TraceVerde	OpenLIT	Traceloop/OpenLLMetry	Langfuse
Zero-code setup	Yes	Yes	Yes	SDK required
LLM providers	19+	25+	15+	Via integrations
Multi-agent frameworks	8 (CrewAI, LangGraph, ADK, AutoGen, OpenAI Agents, Pydantic AI, etc.)	Limited	Limited	Limited
Cost tracking	Automatic (1,050+ models)	Manual config	Manual config	Manual config
GPU metrics (NVIDIA + AMD)	Yes	No	No	No
MCP tool instrumentation	Yes (databases, caches, vector DBs, queues)	Limited	Limited	No
Evaluation (PII, toxicity, bias, hallucination, prompt injection)	Built-in (6 detectors)	No	No	Separate service
OpenTelemetry native	Yes	Yes	Yes	Partial
License	Apache-2.0	Apache-2.0	Apache-2.0	MIT

What Gets Instrumented?

LLM Providers (19+)

OpenAI, OpenRouter, Anthropic, Google AI, Google GenAI, AWS Bedrock, Azure OpenAI, Cohere, Mistral AI, Together AI, Groq, Ollama, Vertex AI, Replicate, HuggingFace, SambaNova, Sarvam AI, Hyperbolic, LiteLLM

See all providers with examples >>

Multi-Agent Frameworks (8)

CrewAI, LangGraph, Google ADK, AutoGen, AutoGen AgentChat, OpenAI Agents SDK, Pydantic AI, AWS Bedrock Agents

See all frameworks with examples >>

MCP Tools (20+)

Databases: PostgreSQL, MySQL, MongoDB, SQLAlchemy, TimescaleDB, OpenSearch, Elasticsearch, FalkorDB Caching: Redis | Queues: Kafka, RabbitMQ | Storage: MinIO Vector DBs: Pinecone, Weaviate, Qdrant, ChromaDB, Milvus, FAISS, LanceDB

See all MCP tools >>

Built-in Evaluation (6 Detectors)

PII Detection (GDPR/HIPAA/PCI-DSS), Toxicity Detection, Bias Detection, Prompt Injection Detection, Restricted Topics, Hallucination Detection

See all evaluation features with examples >>

Screenshots

OpenAI traces with token usage, costs, and latency

More screenshots

Ollama (Local LLM)

SmolAgents with Tool Calls

GPU Metrics

OpenSearch Dashboard

Key Features

Automatic Cost Tracking

1,050+ models across 30+ providers with per-request cost breakdown. Supports differential pricing (prompt vs completion), reasoning tokens, cache pricing, and custom model pricing.

# Cost tracking is enabled by default - just instrument and go
genai_otel.instrument()

# Or add custom pricing for proprietary models
export GENAI_CUSTOM_PRICING_JSON='{"chat":{"my-model":{"promptPrice":0.001,"completionPrice":0.002}}}'

Cost tracking guide >>

GPU Metrics (NVIDIA + AMD)

Real-time monitoring of utilization, memory, temperature, power, PCIe throughput, throttling, and ECC errors. Multi-GPU aggregate metrics included.

pip install genai-otel-instrument[gpu]      # NVIDIA
pip install genai-otel-instrument[amd-gpu]  # AMD

GPU metrics guide >>

Multi-Agent Tracing

Complete span hierarchy for agent frameworks with automatic context propagation:

Crew Execution
  +-- Agent: Senior Researcher (gpt-4)
  |     +-- Task: Research OpenTelemetry
  |           +-- openai.chat.completions (tokens: 1250, cost: $0.03)
  +-- Agent: Technical Writer (ollama:llama2)
        +-- Task: Write blog post
              +-- ollama.chat (tokens: 890, cost: $0.00)

Multimodal Observability (v1.1.0)

First-class capture of image, audio, video, and document content parts on OpenAI, Anthropic, Google Gemini, and Groq spans. Bytes are offloaded to your configured object store (MinIO / S3 / filesystem / HTTP) and referenced from spans by URI — they never appear inline in span attributes.

# Opt in (default is off — text-only behaviour is byte-identical to 1.0.x)
export GENAI_OTEL_MEDIA_CAPTURE_MODE=full
export GENAI_OTEL_MEDIA_STORE=minio
export GENAI_OTEL_MEDIA_STORE_ENDPOINT=http://localhost:9000
export GENAI_OTEL_MEDIA_STORE_ACCESS_KEY=...
export GENAI_OTEL_MEDIA_STORE_SECRET_KEY=...
# Optional: plug in a redactor before upload
export GENAI_OTEL_MEDIA_REDACTOR=genai_otel.media.redactors.face_blur

Spans get a flat, queryable attribute namespace — gen_ai.prompt.{n}.content.{m}.{type, media_uri, media_mime_type, media_byte_size, media_source} — that is being proposed upstream to OpenTelemetry semantic-conventions (issue #3672).

Multimodal guide >>

Safety & Evaluation

genai_otel.instrument(
    enable_pii_detection=True,       # GDPR/HIPAA/PCI-DSS compliance
    enable_toxicity_detection=True,  # Perspective API + Detoxify
    enable_bias_detection=True,      # 8 bias categories
    enable_prompt_injection_detection=True,
    enable_hallucination_detection=True,
    enable_restricted_topics=True,
)

Evaluation guide with 50+ examples >>

Configuration

# Required
export OTEL_SERVICE_NAME=my-llm-app
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318

# Optional
export GENAI_ENABLE_GPU_METRICS=true
export GENAI_ENABLE_COST_TRACKING=true
export GENAI_SAMPLING_RATE=0.5                    # Reduce volume in production
export GENAI_ENABLED_INSTRUMENTORS=openai,crewai  # Select specific instrumentors

Full configuration reference >>

Backend Integration

Works with any OpenTelemetry-compatible backend:

Jaeger, Zipkin, Prometheus, Grafana, Datadog, New Relic, Honeycomb, AWS X-Ray, Google Cloud Trace, Elastic APM, Splunk, SigNoz, self-hosted OTel Collector

Pre-built Grafana dashboard templates included.

Examples

90+ ready-to-run examples covering every provider, framework, and evaluation feature:

examples/
+-- openai/              # OpenAI chat, embeddings
+-- anthropic/           # Anthropic + PII/toxicity detection
+-- ollama/              # Local models + all evaluation features
+-- crewai_example.py    # Multi-agent crew orchestration
+-- langgraph_example.py # Stateful graph workflows
+-- google_adk_example.py # Google Agent Development Kit
+-- autogen_example.py   # Microsoft AutoGen agents
+-- pii_detection/       # 10 PII examples (GDPR, HIPAA, PCI-DSS)
+-- toxicity_detection/  # 8 toxicity examples
+-- bias_detection/      # 8 bias examples (hiring compliance, etc.)
+-- prompt_injection/    # 6 injection defense examples
+-- hallucination/       # 4 hallucination detection examples
+-- ...                  # And many more

Browse all examples >>

Who Uses TraceVerde?

TraceVerde is used by developers and teams building production GenAI applications. If you're using TraceVerde, we'd love to hear from you!

Add your company | Join Discord

Community

• Documentation - Full guides, API reference, and tutorials
• Discord - Chat with the community
• GitHub Issues - Bug reports and feature requests
• Contributing - How to contribute

License

Copyright 2025 Kshitij Thakkar. Licensed under the Apache License 2.0.