Framework Integrations

pip install kalibr[crewai] crewai openai anthropic

from kalibr import Router
from crewai import Agent, Task, Crew

# Create Kalibr router
router = Router(
 goal="research_task",
 paths=["gpt-4o-mini", "claude-sonnet-4-20250514"]
)

# Get LangChain-compatible LLM
llm = router.as_langchain()

# Use with CrewAI
researcher = Agent(
 role="Researcher",
 goal="Find accurate information",
 backstory="You are a research assistant.",
 llm=llm, # Kalibr handles model selection
 verbose=True
)

task = Task(
 description="Research the history of Python programming language.",
 expected_output="A summary of Python's history.",
 agent=researcher
)

crew = Crew(agents=[researcher], tasks=[task])
result = crew.kickoff()

# Report outcome to Kalibr
router.report(success=len(str(result)) > 100)

pip install kalibr[langchain] langchain langchain-openai langchain-anthropic

from kalibr import Router
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser

router = Router(
 goal="summarize_text",
 paths=["gpt-4o-mini", "claude-sonnet-4-20250514"]
)

llm = router.as_langchain()

prompt = ChatPromptTemplate.from_template("Summarize this: {text}")
chain = prompt | llm | StrOutputParser()

result = chain.invoke({"text": "Long article text here..."})

router.report(success=len(result) > 50)

pip install kalibr[openai-agents] openai-agents

from kalibr import Router
router = Router(
 goal="agent_task",
 paths=["gpt-4o", "gpt-4o-mini"]
)

# Get routing decision
from kalibr import get_policy
policy = get_policy(goal="agent_task")
model = policy["recommended_model"]

# Use with OpenAI Agents SDK
from agents import Agent, Runner

agent = Agent(
 name="Assistant",
 instructions="You are a helpful assistant.",
 model=model,
)
result = Runner.run_sync(agent, "Your task here")

# Report outcome
router.report(success=len(result.final_output) > 0)

pip install kalibr huggingface_hub

import kalibr # instruments InferenceClient automatically
from huggingface_hub import InferenceClient

client = InferenceClient()
# All 17 task methods are now traced with cost tracking

# Route between HuggingFace models
from kalibr import Router
router = Router(
 goal="transcribe_call",
 paths=["openai/whisper-large-v3", "facebook/seamless-m4t-v2-large"],
 success_when=lambda output: len(output) > 50
)
result = router.execute(task="automatic_speech_recognition", input_data=audio_bytes)

pip install kalibr openai

export DEEPSEEK_API_KEY=sk-... # from platform.deepseek.com

import kalibr
from kalibr import Router

# Route between DeepSeek models
router = Router(
 goal="classify_icp",
 paths=["deepseek-chat", "deepseek-reasoner"],
 success_when=lambda output: len(output) > 0
)
response = router.completion(messages=[{"role": "user", "content": "Is this company a good ICP fit?"}])

# Mix DeepSeek with other providers, Kalibr learns which works best
router = Router(
 goal="classify_icp",
 paths=["gpt-4o-mini", "deepseek-chat", "claude-sonnet-4-20250514"],
)
response = router.completion(messages=[...])

pip install kalibr openai

export NEBIUS_API_KEY=... # from studio.nebius.ai

import kalibr
from kalibr import Router

router = Router(
 goal="research",
 paths=["nebius/meta-llama/Llama-3.3-70B-Instruct", "deepseek-chat"],
)
response = router.completion(messages=[{"role": "user", "content": "Summarize the latest in AI"}])

pip install kalibr httpx

export TAVILY_API_KEY=tvly-... # from app.tavily.com

import kalibr
from kalibr import Router

# Compete Tavily against an LLM on web research
router = Router(
 goal="web_scraping",
 paths=["tavily/advanced", "deepseek-chat"],
 success_when=lambda out: len(out) > 100,
)
response = router.completion(messages=[{"role": "user", "content": "Latest AI benchmark results 2025"}])

pip install kalibr[voice] # ElevenLabs + Deepgram + OpenAI Audio
pip install kalibr[elevenlabs] # ElevenLabs only
pip install kalibr[deepgram] # Deepgram only

import kalibr # instruments ElevenLabs + OpenAI Audio automatically
from kalibr import Router

# Route between TTS providers, Kalibr learns which sounds better / costs less
router = Router(
 goal="narrate",
 paths=["tts-1", "eleven_multilingual_v2"],
 success_when=lambda _: True # or evaluate audio quality downstream
)
result = router.synthesize("Your agent completed the task.", voice="alloy")
audio_bytes = result.audio
# result.cost_usd, result.model, result.kalibr_trace_id also available

router = Router(
 goal="transcribe_calls",
 paths=["whisper-1", "nova-2"], # OpenAI Whisper or Deepgram Nova
 success_when=lambda text: len(text) > 20
)
result = router.transcribe(audio_bytes, audio_duration_seconds=30.0)
print(result.text) # transcribed text

from kalibr_voice import KalibrLiveKitInstrumentor, KalibrPipecatInstrumentor

KalibrLiveKitInstrumentor().instrument() # LiveKit Agents pipeline
KalibrPipecatInstrumentor().instrument() # Pipecat processors

pip install kalibr[voice] # ElevenLabs + Deepgram
pip install kalibr[elevenlabs] # ElevenLabs only
pip install kalibr[deepgram] # Deepgram only

import kalibr
from kalibr import Router

# Route between ElevenLabs and OpenAI TTS
router = Router(
 goal="narrate",
 paths=["eleven_multilingual_v2", "tts-1"],
 success_when=lambda audio: len(audio) > 0,
)
result = router.synthesize("Hello, welcome to Kalibr.", voice="alloy")
audio_bytes = result.audio
# result.cost_usd, result.model, result.kalibr_trace_id

import kalibr
from kalibr import Router

# Route between OpenAI Whisper and Deepgram Nova
router = Router(
 goal="transcribe_calls",
 paths=["whisper-1", "nova-2"],
 success_when=lambda text: len(text) > 10,
)
result = router.transcribe(audio_bytes, audio_duration_seconds=30.0)
transcript = result.text
# result.cost_usd, result.kalibr_trace_id

from kalibr_voice import KalibrLiveKitInstrumentor, KalibrPipecatInstrumentor

KalibrLiveKitInstrumentor().instrument() # LiveKit Agents pipeline
KalibrPipecatInstrumentor().instrument() # Pipecat processors

/plugin add kalibr

/kalibrize

run_pipeline(
 goal="summarization",
 messages=[{"role": "user", "content": "Summarize: ..."}]
)
# Returns: result, model_used, healed, heal_count, models_tried, latency_ms