context-cut 0.1.0

Agent context budget profiler and auto-optimizer for LLM pipelines

ContextCut

Your LLM agent is burning tokens. Most of them are waste. ContextCut tells you exactly where, and fixes it automatically.

The problem

Most production agents waste 40–70% of their token budget on:

• Message history that never gets pruned
• Tool schemas injected into every single call
• The same context block re-sent across every node
• RAG chunks larger than needed
• System prompts repeated verbatim on every turn

Install

pip install context-cut

Quickstart (no API key needed)

python examples/no_api_key_example.py

Usage — one decorator

import contextcut

@contextcut.wrap(model="gpt-4o", verbose=True)
async def run_my_agent(task: str):
    result = await my_langgraph_graph.ainvoke({"messages": [...]})
    return result

await run_my_agent("Analyze Q4 sales")
report = contextcut.get_last_report()

CLI

contextcut analyze --file my_agent.py --task "Analyze Q4 sales" --export html
contextcut analyze --file my_agent.py --task "..." --auto-patch
contextcut compare --before run_abc --after run_xyz
contextcut serve

Dashboard

pip install "context-cut[dashboard]"
contextcut serve

Open http://localhost:3000

LangGraph integration

from contextcut.integrations.langgraph import LangGraphContextCutCallback

callback = LangGraphContextCutCallback(model="gpt-4o")
result = graph.invoke(task, config={"callbacks": [callback]})
report = contextcut.profile(callback.get_intercepts())

License

MIT