Deploy AI agents in 5 lines of code.

Custodian Labs has launched a Python SDK that enables developers to deploy AI agents in five lines of code, handling infrastructure, hosting, and chat UI automatically. The tool supports adding data sources like CSV and PDF files for retrieval-augmented generation, and provides a shareable URL for each deployed agent. The company aims to eliminate the weeks of plumbing typically required for building and deploying AI agents.

Build AI-agents in 5 lines of code. Skip the set up & infrastructure. Live and running. python from custodian labs import Custodian app = Custodian model="gpt-4o", system prompt="You are a concise, helpful assistant.", .deploy print app.chat "Hello " .response print app.chat url ← live, shareable URL Runnable Colab notebook here https://colab.research.google.com/gist/SherryCodes123/065d3b67eab16bdca416836e0d39475a/simple-ai-agents-rag-multi-agents.ipynb . DIYing this: FastAPI behind a reverse proxy + Redis for sessions + a small frontend + an auth layer + a vector DB and ingestion pipeline. All of it is annoying. Most teams burn weeks on plumbing before the interesting work even starts. Grab a free API key from the dashboard https://dashboard.custodianlabs.io , then: pip install -q custodian-labs python import os from getpass import getpass os.environ "CUSTODIAN SDK API KEY" = getpass "API key: " python from custodian labs import Custodian app = Custodian model="gpt-4o", system prompt="You are a concise, helpful assistant.", .deploy reply = app.chat "In one sentence, what can you help me with?" print reply.response print "\nShareable chat URL:", app.chat url What you get back: app — handle to a live hosted agent. reply.response — the text. reply.session id — pass it to the next .chat to continue the conversation. app.chat url — live URL to a hosted chat UI. Paste in Slack, share with PMs, done. python from custodian labs import Custodian agent = Custodian model="gpt-4o", system prompt= "You answer questions about the car dataset you've been given. " "Be specific and cite the numbers." , agent.add data source file "data examples/car info.csv" app = agent.deploy reply = app.chat "Which SUV has the best city MPG, and what is its annual maintenance cost?" print reply.response print "\nShareable chat URL:", app.chat url add data source file handles chunking, embedding, and retrieval at chat time. Works on CSVs, PDFs, and the usual suspects — calling code doesn't change whether you point it at a CSV or a folder of contracts. Same shape for all of them: write a system prompt, attach docs, deploy, share the URL. The Colab notebook https://colab.research.google.com/gist/SherryCodes123/065d3b67eab16bdca416836e0d39475a/simple-ai-agents-rag-multi-agents.ipynb runs end-to-end with sample data — bring no files, just a free key from the dashboard https://dashboard.custodianlabs.io . Should take ~1 min. I'd genuinely love feedback — what's missing, what's confusing, what would make you actually use it. Feature requests very welcome. Drop them in the comments, or email sherry@custodianlabs.io if you build something with it or break it in an interesting way . Next posts coming on multi-agent teams with topic routing, and the PII / proprietary-data masking layer for legal and healthcare agents.