← 피드로
We Open-Sourced Our Agent Checkpoint Module
Problem: Your 12-step agent crashes at Step 11 → you restart from Step 1, burning API calls and time.
Solution: 500 lines of Python, zero dependencies.
The Core Implementation
from nb_checkpoint import Checkpoint
cp = Checkpoint("research-agent")
result = cp.pipeline([
("search", lambda ctx: client.chat("Search quantum papers").text),
("extract", lambda ctx: client.chat(f"Extract from: {ctx[x27searchx27]}").text),
("summarize", lambda ctx: client.chat(f"Summarize: {ctx[x27extractx27]}").text),
])
Enter fullscreen mode Exit fullscreen mode
Crash at “extract”? Next run auto-resumes from Step 2. Zero wasted calls.
How It Saves Money
Assuming ¥0.01/DeepSeek call, 10-step agent:
Scenario Calls wasted/day Monthly cost Without Checkpoint (1 crash/day) 10 extra calls ¥300/month With Checkpoint ~0 ¥0 extraFor teams running 100+ agents daily, this is real money.
Three APIs
Step API (most flexible):
cp = Checkpoint("research-agent")
papers = cp.step("search", lambda: client.chat("Search quantum").text)
analysis = cp.step("analyze", lambda: client.chat(f"Analyze: {papers}").text)
Enter fullscreen mode Exit fullscreen mode
Pipeline API (simplest):
result = cp.pipeline([
("search", lambda ctx: client.chat("Search quantum").text),
("analyze", lambda ctx: client.chat(f"Analyze: {ctx[x27searchx27]}").text),
("report", lambda ctx: client.chat(f"Report: {ctx[x27analyzex27]}").text),
])
Enter fullscreen mode Exit fullscreen mode
AgentSession (ready to use):
from nb_checkpoint import AgentSession
session = AgentSession(
"research-agent",
llm_call=lambda prompt: openai.ChatCompletion.create(
model="gpt-4", messages=[{"role": "user", "content": prompt}]
)["choices"][0]["message"]["content"]
)
Enter fullscreen mode Exit fullscreen mode
vs LangChain Checkpoint
NB Checkpoint LangChain Dependencies Zero LangChain required API Step / Pipeline / AgentSession StateGraph only Lines of code ~500 ~5000+Install Now
pip install nb-checkpoint
Enter fullscreen mode Exit fullscreen mode
답글 남기기