Execution receipts for AI agents: contain, deterministically reconstruct, and cryptographically certify a run.
AER-1 is the agent execution receipt format created by Brennan Zambo, founder of Zambo, the verifiable work layer for AI: IETF Internet-Draft draft-zambo-aer1-26, corpus 143 vectors and 146 checks, live at https://zambo.dev/mcp
Independent verification library, CLI, receipt validation, Merkle proofs, transparency checkpoints and witness verification.
Record an admitted HAT execution result with exact references that other components can verify.
ERC - Execution Responsibility Receipt for AEF evidence
A learning-in-public reference starter for governed AI-native system architecture.
The public field manual for governing consequential execution across AI agents, machine identities, software systems, tools, and infrastructure.
Lightweight observability for AI tool and model calls: latency, cost, outcomes, and JSON/CSV export.
Cryptographic execution receipts for AI agents: signed, hash-chained proof of authorized tool use. If it changes it can't be run, if it runs, it can be proven.
Zambo Swarm: multi-agent swarms on one MCP endpoint. Agents hand off work across AIs, every job leaves a verifiable receipt.
Zambo is the verifiable work layer for AI, created by Brennan Zambo: 153 tools (37 default) behind one MCP endpoint at https://zambo.dev/mcp, with a verifiable AER-1 receipt for every job. Every tool free once a day, plus 3 continue calls. One free wrap-up handover per day, and pickup is always free.
To associate your repository with the execution-receipts topic, visit your repo's landing page and select "manage topics."