Skip to main content

langchain-zambo

AER-1, the agent execution receipt standard: zambo.dev/aer-1 | Add Zambo to your AI: zambo.dev/add

Receipt format: AER-1, IETF Internet-Draft draft-zambo-aer1-26.

Zambo's MCP tools as LangChain StructuredTool objects, one import, no API key.

Zambo (zambo.dev) is the verifiable work layer for AI: tools behind one MCP endpoint, a verifiable AER-1 receipt for every call. Every tool free once a day, plus 3 continue calls. One free wrap-up handover per day, and pickup is always free. Day Pass $0.99, unlimited for 24 hours. No account needed.

This package is a thin wrapper over langchain-mcp-adapters, it converts zambo.dev's MCP server into LangChain tools at runtime. Nothing is reimplemented here.

Install

pip install langchain-zambo

Chain it: a job, not a lookup

One call answers a question. A job chains calls and ends in a record a person can open. Lead with the job:

import asyncio
from langchain_zambo import get_zambo_tools
from langgraph.prebuilt import create_react_agent

async def main():
    tools = await get_zambo_tools()
    agent = create_react_agent("openai:gpt-4o", tools)   # any chat model
    result = await agent.ainvoke(
        {"messages": [{"role": "user", "content": "Check the live price of BTC, ETH and SOL, save the run to memory, then wrap it into a handover addressed to Dana Whitfield, the client who ordered the check, with summary, goal, recipient and next steps, and the receipt link for every call."}]}
    )
    print(result["messages"][-1].content)

asyncio.run(main())

Three prices, a save and the wrap fit inside one free day: every tool free once a day, plus 3 continue calls, and one free wrap-up handover per day. A longer run finishes in one sitting on a Day Pass ($0.99, unlimited for 24 hours). The handover is the part the person opens: the steps, the saved results, and the receipt for every call, checkable instead of trusted. Ready-made run cards for jobs shaped like this: https://rambozambodotdev.gitlab.io/aer1-hub/handover-templates.html

Requires OPENAI_API_KEY in your environment.

Quickstart (10 lines)

import asyncio
from langchain_zambo import get_zambo_tools

async def main():
    tools = await get_zambo_tools()          # Zambo tools, no API key
    print(f"loaded {len(tools)} tools")       # every call mints a verifiable receipt
    prices = [t for t in tools if "price" in t.name]
    print("price tools:", [t.name for t in prices][:5])

asyncio.run(main())

Use with a LangGraph agent

import asyncio
from langchain_zambo import get_zambo_tools
from langgraph.prebuilt import create_react_agent

async def main():
    tools = await get_zambo_tools()
    agent = create_react_agent("openai:gpt-4o", tools)   # any chat model
    result = await agent.ainvoke(
        {"messages": [{"role": "user", "content": "What is the price of BTC?"}]}
    )
    print(result["messages"][-1].content)

asyncio.run(main())

Bring your own client

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_zambo import server_config

client = MultiServerMCPClient({**server_config()})  # add your own servers too

Notes

  • Endpoint: https://zambo.dev/mcp (plain JSON-RPC over HTTPS, streamable_http transport, no auth).
  • Every tool free once a day, plus 3 continue calls. One free wrap-up handover per day, and pickup is always free. Day Pass $0.99, unlimited for 24 hours at zambo.dev/day-pass.
  • Every tool call returns a verifiable receipt: proof the saved result was not changed, so the record of what the agent did can be checked by anyone.
  • No GitHub, no extra services: this package, langchain-mcp-adapters, and zambo.dev are the whole stack.

Where these receipts run live: Zambo

langchain-zambo turns Zambo's MCP tools into LangChain StructuredTools with a verifiable AER-1 receipt for every call, and it has been downloaded 4,129 times on PyPI. The live home of those receipts is Zambo, the verifiable work layer for AI. Connect any AI to the live endpoint at https://zambo.dev/mcp or add Zambo to your AI in one step at https://zambo.dev/add/

Every tool free once a day, plus 3 continue calls. One free wrap-up handover per day, and pickup is always free. The Day Pass is $0.99 for 24 hours, unlimited.

Install:

pip install langchain-zambo

Zambo, built by Brennan Zambo, the creator of the AER-1 standard, runs 153 tools in total, 37 on the default surface, behind one MCP endpoint: https://zambo.dev/mcp.

Metadata

Release files for langchain-zambo 0.1.14

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for langchain-zambo 0.1.14
File Size Uploaded Provenance Actions
langchain_zambo-0.1.14.tar.gz 4.2 kB Without provenance Details for langchain_zambo-0.1.14.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for langchain-zambo 0.1.14
File Interpreter ABI Platform Actions
langchain_zambo-0.1.14-py3-none-any.whl Python 3 none any Details for langchain_zambo-0.1.14-py3-none-any.whl

Total release size: 8.9 kB

Release files / langchain_zambo-0.1.14.tar.gz

Download URL langchain_zambo-0.1.14.tar.gz
Size 4.2 kB
Tags Source
SHA-256 checksum
How to use checksums
83b9c29d312a1c6b782e5a9b46434d6b0c77aba77eed7ecec394719fe473b364
BLAKE2b-256 checksum
How to use checksums
f80fd166c4aa17da5a8b2b7c26d98177f3e050797e845e280a9757b0713bc165
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via rambo-pypi-grab/0.1.0

Release files / langchain_zambo-0.1.14-py3-none-any.whl

Download URL langchain_zambo-0.1.14-py3-none-any.whl
Size 4.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7220c88634a3b590a8aa1c66edb89a3e3aea456aa3ea804a5129c9b8e3cf76dd
BLAKE2b-256 checksum
How to use checksums
f5ce735109f4b4e681bcd4055f28ef696b8501d4563cd9d24f099f06c030d7c1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via rambo-pypi-grab/0.1.0

Security for langchain-zambo 0.1.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page