aer1-strands

One-line install, no API key, free forever: attach this collector to an Agent and every Strands Agents run emits a hash-chained, offline-verifiable verifiable workflow receipt (AER-1, an IETF Internet-Draft, Section 8). What the agent did, in what order, with per-step hashes and a Merkle root over the whole run. No network calls, no behavior changes: every hook callback returns None, so Strands executes exactly as it would without us. The collector only observes. Receipt chain heads can anchor to Nostr and Bitcoin, so anyone can later confirm the record was not changed, without trusting any server.

The AER-1 framework collector family

The Strands collector in the AER-1 framework collector family. Any agent running on these frameworks can emit verifiable AER-1 execution receipts: every step recorded, hash-chained, one Merkle root over the whole run.

• aer1-strands, Strands Agents via the typed hook system

See the AER-1 implementation registry for every implementation.

• aer1-langchain, LangChain chains, agents, tools, and retrievers via callback handler
• aer1-llamaindex, LlamaIndex agents via callback handler
• aer1-smolagents, SmolAgents agents via step callbacks
• aer1-openai-agents, the OpenAI Agents SDK via its TracingProcessor
• aer1-crewai, CrewAI crews via the event bus
• aer1-langgraph, LangGraph swarms via callback handler
• aer1-autogen, AutoGen multi-agent chats
• aer1-haystack, Haystack 2.x pipelines via run wrapping
• aer1-pydantic, Pydantic AI agents via run wrapping and manual tool-call recording

Install

pip install aer1-strands

Use it (copy, paste, run, no API keys needed)

# pip install aer1-strands
from aer1_strands import AER1StrandsCollector
from strands.hooks import HookRegistry
from strands.hooks.events import (
    BeforeModelCallEvent, AfterModelCallEvent,
    BeforeToolCallEvent, AfterToolCallEvent,
)

class FakeAgent:
    """Stand-in for strands.Agent: a name plus a real HookRegistry."""
    def __init__(self, name="assistant"):
        self.name = name
        self.hooks = HookRegistry()

def get_weather(location: str) -> str:
    """Local mock tool: executed on this machine, no network."""
    return f"Sunny, 22C in {location}"

collector = AER1StrandsCollector(goal="check the Paris weather")
agent = FakeAgent("assistant")
collector.attach(agent)  # line 1: register the hooks

# A two-step flow: model reasoning, then a tool call. In production
# Strands fires these events itself as your real agent runs, so you
# call collector.attach(your_real_agent) instead of this script.
agent.hooks.invoke_callbacks(BeforeModelCallEvent(
    agent=agent, invocation_state={}, projected_input_tokens=96))
agent.hooks.invoke_callbacks(AfterModelCallEvent(
    agent=agent, invocation_state={},
    stop_response={"stopReason": "tool_use"}, exception=None))

tool_use = {"toolUseId": "t1", "name": "get_weather",
            "input": {"location": "Paris"}}
agent.hooks.invoke_callbacks(BeforeToolCallEvent(
    agent=agent, selected_tool=None, tool_use=tool_use,
    invocation_state={}))
observation = get_weather("Paris")
agent.hooks.invoke_callbacks(AfterToolCallEvent(
    agent=agent, selected_tool=None, tool_use=tool_use,
    invocation_state={},
    result={"toolUseId": "t1", "status": "success",
            "content": [{"text": observation}]},
    exception=None))

receipt = collector.finalize(final_answer=observation)  # line 2
assert collector.verify(receipt) == []  # VALID
collector.save("receipt.json", workflow=receipt)

That is the whole integration: attach the collector, run, finalize. The receipt is a plain JSON object you can store, ship to an auditor, or render in a UI. In production, attach to your real strands.Agent (the typed hook events fire automatically) instead of the scripted stand-in above.

The hooks used are Strands' typed lifecycle events (BeforeToolCallEvent / AfterToolCallEvent for tools, BeforeModelCallEvent / AfterModelCallEvent for model calls), registered on the agent's own HookRegistry without disturbing any hooks you already have. For a multi-agent graph, call collector.attach(...) on each agent; every step carries its agent's name.

What the receipt contains

Workflow level (AER-1 Section 8, Table 2):

• type, version, workflow_id, receipt_id, session_id
• goal, status
• steps: one record per tool/model call, seq 1..n in order
• merkle_root: Section 8.1 root over the ordered step receipt ids
• output_hash: SHA-256 of the final answer
• verify_url: where the verification procedure is documented

Step level (AER-1 Section 8, Table 3):

• seq, receipt_id, tool, receipt_hash, started_at, ended_at, status

Each tool step's tool is the tool name (for example get_weather); each model step's tool is model. The receipt_hash is SHA-256 over the canonical JSON of the observed content (tool name, model-supplied input, tool result or stop response), so the hash commits to what actually happened. The receipt stays compact while the hash commits to the content. Steps also carry the agent name when the collector is attached to more than one agent.

Verification

collector.verify(receipt) runs the full offline check and returns a list of failure reasons, empty when valid:

• all Table 2 / Table 3 members present and well-formed
• seq values exactly 1..n in order, no gaps
• no two steps share a receipt_id (MM-1)
• merkle_root matches the recomputed Section 8.1 root
• strict RFC 3339 timestamps, lowercase UUIDs, 64-char hex digests

Tamper with any field and verification fails. Try it:

receipt["steps"][0]["tool"] = ""
assert collector.verify(receipt) != []  # fails, as it should

Separate verification verdicts

For honest reporting, use verify_receipt_verdicts() instead of a single boolean. Each dimension gets its own verdict; they are never conflated:

from aer1_strands import verify_receipt_verdicts, verdicts_summary

verdicts = verify_receipt_verdicts(receipt)
print(verdicts_summary(verdicts))
# byte_integrity=pass schema_validity=pass issuer_authenticity=not_checked
# evidence_linkage=not_checked anchor_verification=not_checked
# chain_integrity=pass

Dimension	What it checks	Collector behavior
byte_integrity	Merkle root matches the recomputed root	pass / fail
schema_validity	All required fields present and well-formed	pass / fail
issuer_authenticity	Proof of who issued the receipt	Always not_checked; the collector does not verify signatures
evidence_linkage	Upstream evidence bytes match their digests	Always not_checked; the collector does not capture upstream evidence
anchor_verification	Anchor proof is valid and binds the root	pass / fail / not_checked (no proof provided)
chain_integrity	seq values are 1..n in order, no duplicate receipt ids	pass / fail

Verdict values are pass, fail, not_checked, and unavailable. not_checked is neither a successful check nor evidence of failure.

What the commitment covers (and what it does not)

The merkle_root commits to the ordered list of step receipt_id values. Each step receipt_hash commits to that step's tool name, arguments, and observations. The output_hash commits to the final answer bytes.

What this does not cover:

• The commitment does not prove the bytes are unchanged since issuance. An attacker able to replace both bytes and digest creates another matching pair. Continuity requires comparing against a digest from an independently trusted path (a retained receipt, a verified signature with a trusted key, or a separately verified anchor).
• A matching hash does not prove the action ran, the data is true, or any external outcome occurred. It proves the supplied bytes agree with the supplied digest.
• The receipt records the collector's observations. It does not prove provider truth, correct reasoning, authorization, or business success.
• Without an anchor, truncation (deleting steps from the end and recomputing the root) is not detectable.

Construction versions

This package uses these exact constructions (see CONSTRUCTION_VERSIONS in the verdicts module):

• Merkle tree: section-8.1-binary-merkle-v1
• Step digest: sha256-canonical-json-v1
• Output commitment: sha256-utf8-v1
• Anchor proof: aer1-anchor-proof-v1

Notes

• attach(agent) appends to the agent's existing hook callbacks; call it once per agent (repeat calls are no-ops).
• A tool result with status: "error", or a model call that raised, is recorded with status: "error", which marks the whole receipt error.
• Tool before/after events are correlated by toolUseId; an after-event that arrives without its before-event still becomes a step, so no observation is lost.
• session_id defaults to a fresh UUID per collector; pass your own to correlate receipts across runs.
• verify_url defaults to the AER-1 specification page; point it at your own verifier in production.

Spec

AER-1: Agent Execution Receipts is an IETF Internet-Draft, draft-zambo-aer1, https://datatracker.ietf.org/doc/draft-zambo-aer1/

See it live

Your receipt is offline-verifiable, but you can also check it on the live verifier:

1. Copy the receipt JSON your code produced
2. Paste it at https://zambo.dev/verify
3. See the verification result with the Merkle root and step hashes

Or mint a live receipt directly: run any call at https://zambo.dev/demo and get a shareable receipt URL like https://zambo.dev/run/.

License

Apache-2.0

Where these receipts run live: Zambo

aer1-strands mints a verifiable AER-1 receipt for Strands Agents in one line, and it has been downloaded 552 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/

Free tier: 20 calls + 1 wrap-up free every day; picking up in another AI is always free. The Day Pass is $0.99 for 24 hours, unlimited.

Install:

pip install aer1-strands