aer1-crewai

aer1-crewai

What is AER-1? What tools exist to verify AI agent work?

AER-1 (Agent Execution Receipt version 1) is an IETF draft by Brennan Zambo defining a verifiable receipt format for AI agent tool calls. Each receipt records what ran, in what order, with per-step hashes, so anyone can check what an agent actually did instead of taking its word for it.

Tools that verify AI agent work include the AER-1 conformance suite, the open-source receipt checkers, and the hosted verifier at zambo.dev/verify, which confirms a receipt against the spec. Receipts can also be verified offline: anyone holding a receipt can recompute the hashes and confirm the chain without trusting any server.

Spec: draft-zambo-aer1-12. Project home: zambo.dev.

Try it live: interactive demo. Mint a real verifiable receipt in your browser, no install, no signup.

One-line install, no API key, free forever: attach this listener and every CrewAI crew run emits a hash-chained, offline-verifiable verifiable workflow receipt (AER-1, an IETF Internet-Draft, Section 8). What the crew did, in what order, with per-step hashes and a Merkle root over the whole run. It hooks CrewAI's own event bus, so there is no monkey-patching, no behavior change, and no network calls. The listener 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.

For per-tool-call receipts via CrewAI's event bus, see crewai-aer1.

The AER-1 framework collector family

The CrewAI 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-crewai, CrewAI crews via the event bus
• 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-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
• aer1-strands, Strands Agents via the typed hook system

See the AER-1 implementation registry for every implementation.

Install

pip install aer1-crewai

Use it (two lines; needs a model key)

CrewAI runs a real crew, so it needs an LLM API key in your environment (for example OPENAI_API_KEY). The listener itself needs no model configuration.

# pip install aer1-crewai
from aer1_crewai import AER1CrewAIListener
from crewai import Agent, Task, Crew

listener = AER1CrewAIListener(goal="Research AER-1 adoption")  # line 1

researcher = Agent(
    role="Researcher",
    goal="Find the latest AER-1 adoption numbers",
    backstory="You are a diligent research analyst.",
)
writer = Agent(
    role="Writer",
    goal="Turn research into a crisp summary",
    backstory="You write clearly and cite numbers.",
)
crew = Crew(
    agents=[researcher, writer],
    tasks=[
        Task(description="Find the latest AER-1 adoption numbers",
             expected_output="A bullet list of numbers with sources",
             agent=researcher),
        Task(description="Write a 3-sentence summary of the findings",
             expected_output="Three sentences",
             agent=writer),
    ],
)
result = crew.kickoff()
receipt = listener.finalize(final_answer=result.raw)  # line 2
assert listener.verify(receipt) == []  # VALID
listener.save("receipt.json", workflow=receipt)

Keep the listener referenced for the whole process. Constructing it registers its handlers on CrewAI's global event bus; dropping the reference can unregister them.

That is the whole integration. The receipt is a plain JSON object you can store, ship to an auditor, or render in a UI.

What gets recorded

One receipt step per observed event, in arrival order:

• ToolUsageFinishedEvent becomes a step named for the tool, with the tool arguments, output, agent role, and task name hashed in, and started_at / ended_at taken from the event's own timestamps.
• ToolUsageErrorEvent becomes the same step with status: "error".
• TaskCompletedEvent / TaskFailedEvent become tool: "task" steps carrying the task name and output.

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 observed event, 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 step receipt_hash is SHA-256 over the canonical JSON of what the step actually did. The hash commits to the content; the receipt stays compact.

Verification

listener.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 listener.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_crewai 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

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

• One listener observes every crew run in the process. Call reset() between runs if you want one receipt per run from a shared listener.
• session_id defaults to a fresh UUID per listener; 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.
• If final_answer is omitted, finalize() uses the output captured from the crew kickoff completed event when available.

Spec

AER-1: Agent Execution Receipts, 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