Python SDK

Compression SDK for OpenAI. Save 40-60% on every call.

Installation

pip install agentready-sdk openai

Method 1: Compress + Call (Recommended)

Compress your messages first, then call OpenAI directly:

import agentready
from openai import OpenAI
import os

# Step 1 — compress
result = agentready.compress(
    api_key=os.environ["AGENTREADY_API_KEY"],
    messages=[{"role": "user", "content": long_prompt}],
)

# Step 2 — call OpenAI directly
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
response = client.chat.completions.create(
    model="gpt-4o",
    messages=result["messages"],
)
# → Prompt compressed automatically, saving ~50% tokens

Async Compression

import agentready
from openai import AsyncOpenAI
import os

# Async compress + call
result = await agentready.compress_async(
    api_key=os.environ["AGENTREADY_API_KEY"],
    messages=[{"role": "user", "content": "Hello!"}],
)

client = AsyncOpenAI(api_key=os.environ["OPENAI_API_KEY"])
response = await client.chat.completions.create(
    model="gpt-4o",
    messages=result["messages"],
)

Method 2: Compress with Options

Fine-tune compression with additional options:

import agentready
from openai import OpenAI
import os

result = agentready.compress(
    api_key=os.environ["AGENTREADY_API_KEY"],
    messages=[{"role": "user", "content": long_prompt}],
    level="medium",        # light, medium, aggressive
    preserve_code=True,
)

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
response = client.chat.completions.create(
    model="gpt-4o",
    messages=result["messages"],
)

Method 3: Manual Compression

import agentready
import os
agentready.api_key = os.environ["AGENTREADY_API_KEY"]

result = agentready.compress(
    "Your long prompt here...",
    level="medium",        # light, medium, aggressive
    preserve_code=True,
    target_model="gpt-4",
)

print(result.text)              # compressed output
print(result.tokens_saved)      # 1,247
print(result.reduction_percent) # 52.3
print(result.savings_usd)       # 0.0374

LangChain Integration

from agentready.integrations.langchain import TokenCutCallbackHandler
from langchain_openai import ChatOpenAI

import os
handler = TokenCutCallbackHandler(api_key=os.environ["AGENTREADY_API_KEY"])
llm = ChatOpenAI(model="gpt-4o", callbacks=[handler])

# All prompts compressed before sending
response = llm.invoke("Your long context here...")

LlamaIndex Integration

from agentready.integrations.llamaindex import TokenCutPostprocessor

import os
postprocessor = TokenCutPostprocessor(api_key=os.environ["AGENTREADY_API_KEY"])
query_engine = index.as_query_engine(
    node_postprocessors=[postprocessor]
)
response = query_engine.query("What is the system architecture?")

CrewAI Integration

from agentready.integrations.crewai import create_crewai_llm
from crewai import Agent, Task, Crew

import os
llm = create_crewai_llm(
    agentready_key=os.environ["AGENTREADY_API_KEY"],
    openai_key=os.environ["OPENAI_API_KEY"],
    model="gpt-4o",
)

agent = Agent(
    role="Researcher",
    goal="Research AI trends",
    backstory="Expert AI researcher.",
    llm=llm,
)

task = Task(description="Research and summarize AI trends.", agent=agent)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()

Streaming

Compress first, then stream with OpenAI as usual:

import agentready
from openai import OpenAI
import os

result = agentready.compress(
    api_key=os.environ["AGENTREADY_API_KEY"],
    messages=[{"role": "user", "content": long_prompt}],
)

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
stream = client.chat.completions.create(
    model="gpt-4o",
    messages=result["messages"],
    stream=True,
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Pricing

Beta — Free unlimited usage. After beta: pay-per-token, ~60% less than direct API costs.