visibe 0.1.11

AI Agent Observability Platform - Track CrewAI, LangChain, LangGraph, and more

Visibe SDK for Python

Observability for AI agents. Track costs, performance, and errors across your entire AI stack — whether you're using CrewAI, LangChain, LangGraph, AutoGen, Anthropic, or direct OpenAI calls.

---

🚀 Quick Start

pip install visibe

Get your API key at app.visibe.ai → Settings → API Keys, then add one line to your app:

import visibe

visibe.init(api_key="sk_live_your_key_here")

That's it. Every OpenAI, Anthropic, LangChain, LangGraph, CrewAI, AutoGen, and Bedrock call is automatically traced from this point on — no wrappers, no config changes.

The API key can also be set via the VISIBE_API_KEY environment variable so you don't need to pass it in code:

export VISIBE_API_KEY=sk_live_your_key_here

import visibe
visibe.init()

---

🧩 Supported Frameworks

• OpenAI
• Anthropic
• LangChain
• LangGraph
• CrewAI
• AutoGen
• AWS Bedrock

Also works with OpenAI-compatible providers: Azure OpenAI, Groq, Together.ai, DeepSeek, and others.

---

⚙️ Configuration

Option	Type	Default	Description
api_key	str	—	Your Visibe API key. Falls back to VISIBE_API_KEY env var
redact_content	bool	False	Omit prompt and completion text from all traces. Only metadata is sent (tokens, cost, duration, model, errors).
frameworks	list[str]	All detected	Limit auto-instrumentation to specific frameworks (e.g. ["openai", "langgraph"])
debug	bool	False	Enable debug logging

Environment Variables

Variable	Description	Default
VISIBE_API_KEY	Your API key (required)	—
VISIBE_API_URL	Override API endpoint	https://api.visibe.ai
VISIBE_AUTO_INSTRUMENT	Comma-separated frameworks to auto-instrument	All detected
VISIBE_REDACT_CONTENT	Omit prompt/completion text from traces (1 or true)	false
VISIBE_DEBUG	Enable debug logging (1 to enable)	0

---

📊 What Gets Tracked

Metric	Sent when redact_content=True
Cost, tokens, duration	✅
Model & provider	✅
Tool calls (name, duration, success/failure)	✅
Errors (type, message)	✅
Full execution timeline (spans)	✅
Per-agent and per-task cost breakdown	✅
Prompt text	❌ omitted
Completion text	❌ omitted

When redact_content=True, prompt and completion text never leave your codebase. You retain full observability over costs, performance, and errors.

---

📖 Integration Examples

OpenAI

import visibe
from openai import OpenAI

visibe.init()

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}]
)
# Automatically traced — cost, tokens, duration, and content captured.

Anthropic

import visibe
import anthropic

visibe.init()

client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}]
)
# Automatically traced. Streaming (stream=True and .stream()) also supported.

LangChain / LangGraph

import visibe
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

visibe.init()

llm = ChatOpenAI(model="gpt-4o-mini")
graph = create_react_agent(llm, tools)

result = graph.invoke({"messages": [("user", "Your prompt here")]})
# Automatically traced — agent steps, LLM calls, and tool calls captured.

Dynamic pipe chains (prompt | llm | parser) are also automatically traced. Nested sub-graphs are tracked with hierarchical agent names.

CrewAI

import visibe
from crewai import Agent, Task, Crew

visibe.init()

architect = Agent(role="Plot Architect", goal="Design mystery plots", backstory="...")
designer = Agent(role="Character Designer", goal="Create characters", backstory="...")
narrator = Agent(role="Narrator", goal="Write the story", backstory="...")

task1 = Task(description="Create a plot outline", agent=architect, expected_output="...")
task2 = Task(description="Design characters", agent=designer, expected_output="...", context=[task1])
task3 = Task(description="Write the story", agent=narrator, expected_output="...", context=[task1, task2])

crew = Crew(agents=[architect, designer, narrator], tasks=[task1, task2, task3])
result = crew.kickoff()
# Single trace with all agents, LLM calls, and per-task cost breakdown.

Training and testing runs (crew.train(), crew.test()) are traced too.

AutoGen

import visibe
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.agents import AssistantAgent

visibe.init()

model_client = OpenAIChatCompletionClient(model="gpt-4o-mini")
assistant = AssistantAgent("assistant", model_client=model_client)
result = await assistant.run(task="Help me with this task")
# Automatically traced.

AWS Bedrock

import visibe
import boto3

visibe.init()

bedrock = boto3.client("bedrock-runtime", region_name="us-east-1")
response = bedrock.converse(
    modelId="anthropic.claude-3-haiku-20240307-v1:0",
    messages=[{"role": "user", "content": [{"text": "Hello!"}]}]
)
# Automatically traced.

Supports converse, converse_stream, invoke_model, and invoke_model_with_response_stream. Works with all models available via Bedrock — Claude, Nova, Llama, Mistral, and more.

---

📖 API Reference

visibe.init()

Call once at the top of your app, before creating any clients. Returns a Visibe instance.

import visibe

visibe.init(api_key="sk_live_abc123")

track()

Groups multiple LLM calls into a single named trace.

from visibe import Visibe

tracer = Visibe()

with tracer.track(client, name="my-conversation"):
    r1 = client.chat.completions.create(model="gpt-4o-mini", messages=[...])
    r2 = client.chat.completions.create(model="gpt-4o-mini", messages=[...])
# Both calls appear as spans under one trace.

instrument() / uninstrument()

Manually instrument a specific client instance instead of relying on auto-instrumentation.

from visibe import Visibe

tracer = Visibe(api_key="sk_live_abc123")
tracer.instrument(graph, name="my-agent")

result = graph.invoke({"messages": [("user", "Hello")]})

tracer.uninstrument(graph)

# Or use as a context manager for automatic cleanup:
with tracer.instrument(graph, name="my-agent"):
    graph.invoke(...)
# Instrumentation removed automatically on exit.

---

🛡️ Safety Guarantees

• No crashes — every SDK operation is wrapped in try/except
• No latency — all backend calls are fire-and-forget
• No key, no problem — SDK is silently a no-op when no API key is set

No data is sold or shared with third parties. Content is used solely to display traces in your dashboard.

---

🔗 Resources

• visibe.ai — Product website
• app.visibe.ai — Dashboard
• PyPI Package

---

📃 License

MIT — see LICENSE for details.