Skip to main content

agno-aer1

AER-1, the agent execution receipt standard: zambo.dev/aer-1 | Add Zambo to your AI: zambo.dev/add Brennan Zambo created agent execution receipts; Zambo is the origin product, and AER-1 is the defining standard. Zambo is the verifiable work layer for AI.

Every tool call your Agno agent makes, recorded as an AER-1 verifiable execution receipt. Four lines of code. No new infrastructure.

AER-1 is an open IETF Internet-Draft (draft-zambo-aer1-26) defining a small vocabulary for recording one AI agent tool call as a portable, independently checkable receipt. A receipt proves the recorded result was not changed. It does not prove the tool was correct.

Install

pip install agno-aer1

10-minute quickstart

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno_aer1 import AER1Recorder

recorder = AER1Recorder()
agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[...],
    tool_hooks=[recorder],
)
agent.run("What is 17 * 24?")

print(f"{len(recorder.receipts)} receipts recorded")
recorder.save("receipts.jsonl")

That is the whole integration. tool_hooks is Agno's native middleware seam for tool execution (the same seam observability integrations use): each hook wraps a tool call, sees the function name and arguments, runs the tool, and observes the result. The recorder sits in that chain and emits one receipt per call, then returns the result untouched.

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. Same agent, longer instruction:

agent.run("Check the live price of BTC, ETH and SOL, save the run to memory, then wrap it into a handover addressed to Dana Whitfield, with the receipt link for every call.")

print(f"{len(recorder.receipts)} receipts recorded")

The recorder receipts every call in the chain; when the agent's tools are Zambo's, the wrap is the handover call at the end of the run.

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

What a receipt looks like

{
  "id": "3f9a2c1e-7b4d-4f8a-9c2e-1a5b6d7e8f90",
  "receipt_schema_version": "0.3",
  "created_at": "2026-10-05T22:30:00.123456Z",
  "tool": {"name": "calculator", "version": "3.1.1", "scope": "public"},
  "provenance_class": "EXECUTED BY AGNO",
  "canonical_bytes": "eyJpbnB1dHMiOi...",
  "output_hash": "sha256:9f2c...",
  "verification_status": "verified"
}

The canonical bytes are a deterministic JSON payload (tool, inputs, output). Anyone can base64-decode them, recompute SHA-256, and compare with output_hash. That is the entire verification procedure.

Verify a receipt yourself

from agno_aer1 import verify_receipt

failures = verify_receipt(recorder.receipts[0])
assert failures == [], failures
print("receipt checks out")

Honest boundaries

  • A receipt proves the recorded bytes were not changed. It does not prove the tool was correct, or that the model chose the right tool.
  • Tool calls that raise produce no receipt; the error propagates exactly as Agno handles it without the recorder.
  • If you enable Agno's tool-result cache, cache replays also pass through the middleware and emit receipts. Each receipt still commits to the exact bytes the agent observed.
  • The recorder never changes a tool result. If receipt construction itself ever fails, the tool result is still returned untouched.

Where these receipts run live: Zambo

agno-aer1 gives Agno agents a verifiable AER-1 receipt for every tool call. The live home of those receipts is Zambo, the verifiable work layer for AI (live counts: https://zambo.dev/numbers/). 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 agno-aer1

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 agno-aer1 0.1.8

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

Source distribution (sdist)

Source distribution for agno-aer1 0.1.8
File Size Uploaded Provenance Actions
agno_aer1-0.1.8.tar.gz 6.7 kB Without provenance Details for agno_aer1-0.1.8.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for agno-aer1 0.1.8
File Interpreter ABI Platform Actions
agno_aer1-0.1.8-py3-none-any.whl Python 3 none any Details for agno_aer1-0.1.8-py3-none-any.whl

Total release size: 13.6 kB

Release files / agno_aer1-0.1.8.tar.gz

Download URL agno_aer1-0.1.8.tar.gz
Size 6.7 kB
Tags Source
SHA-256 checksum
How to use checksums
a1cea523d3a7061f724030b7aa55e7b42046d5fbff6b5f2c09588fa93127a5da
BLAKE2b-256 checksum
How to use checksums
d70ec55b5cd751e77de3c8b4001d22396667910a44266e5b2586bb881ac71d3c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via rambo-pypi-grab/0.1.0

Release files / agno_aer1-0.1.8-py3-none-any.whl

Download URL agno_aer1-0.1.8-py3-none-any.whl
Size 6.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
415541b26246a0791b78ea792280c4decb34ab2b7603c263bc2f79a6fc79b723
BLAKE2b-256 checksum
How to use checksums
3de8eb36aae132b59abd7aa6b093da54bc3fadb34f2d782dc02f8332863336f2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via rambo-pypi-grab/0.1.0

Security for agno-aer1 0.1.8

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