{"name":"OpenWorkProof: Verifiable Work Contracts for AI Agent Systems","description":"OpenWorkProof is an open protocol designed to bring transparency and accountability to AI agent work. It establishes verifiable contracts for multi-agent systems, ensuring that tasks are authorized, executed within agreed scopes, and independently verifiable. This protocol addresses critical questions about authorization, execution evidence, and human acceptance in AI-driven workflows.","github":"https://github.com/dengyier/OpenWorkProof","url":"https://osrepos.com/repo/dengyier-openworkproof","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/dengyier-openworkproof","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/dengyier-openworkproof.md","json":"https://osrepos.com/repo/dengyier-openworkproof.json","topics":["ai-agents","agent-protocol","verifiable-execution","multi-agent-systems","open-protocol","python","audit","authorization"],"keywords":["ai-agents","agent-protocol","verifiable-execution","multi-agent-systems","open-protocol","python","audit","authorization"],"stars":null,"summary":"OpenWorkProof is an open protocol designed to bring transparency and accountability to AI agent work. It establishes verifiable contracts for multi-agent systems, ensuring that tasks are authorized, executed within agreed scopes, and independently verifiable. This protocol addresses critical questions about authorization, execution evidence, and human acceptance in AI-driven workflows.","content":"## Introduction\nAI agents are becoming increasingly capable, yet verifying their actions and ensuring compliance with human intent remains a significant challenge. OpenWorkProof tackles this by providing an open protocol for AI agent work contracts and verifiable execution. It aims to make every agent action auditable and subject to human judgment, ensuring clarity on who authorized a task, what the agent actually did, and whether it stayed within agreed boundaries.\n\n## Why Use It & Key Benefits\nOpenWorkProof transforms an agent's work into a portable, verifiable chain of evidence. It addresses crucial questions that traditional logs often miss, such as:\n\n*   Who authorized the agent's actions?\n*   Did the agent use only permitted tools and resources?\n*   Are the outputs, like patches or reports, genuinely from the claimed execution?\n*   Can a third party independently review the facts without accessing the original systems?\n\nKey benefits and features include:\n\n*   **Verifiable Evidence Packages**: Each work instance can be exported as a signed evidence package, allowing independent verification by third parties using only the package and public keys.\n*   **Six Connected Facts**: The protocol links work purpose, signed authorization, pre-execution decisions, action receipts, independent verification, and human acceptance.\n*   **Separation of Roles**: Distinct roles like Maintainer, Manager, Developer, Verifier, Sidecar, and Acceptor prevent a single agent from acting as executor, verifier, and final acceptor.\n*   **Human Agency Profile**: This feature ensures that human decision-making remains central, allowing humans to define what capabilities agents can autonomously use, what requires human review, and what is denied.\n*   **Verification and Acceptance Separation**: OpenWorkProof explicitly separates the technical verification of evidence from the human decision of accepting or rejecting the work, preventing \"verified\" from being conflated with \"accepted\" or \"paid.\"\n*   **Verification Integrity**: Mechanisms are in place to ensure that verification results themselves are trustworthy, checking for population capture and control failure signatures.\n\n## Installation\nYou can easily install OpenWorkProof using pip:\n\nbash\npython -m pip install openworkproof\nowp --help\n\n\nFor development or to modify the protocol, you can install from source:\n\nbash\ngit clone https://github.com/dengyier/OpenWorkProof.git\ncd OpenWorkProof\npython -m venv .venv\nsource .venv/bin/activate\npython -m pip install -e .\nowp --help\n\n\n## Examples\nTo see the Human Agency Profile in action, run the minimal example:\n\nbash\npython examples/human_agency_profile_v01.py\n\n\nExpected output will include:\n\ntext\nprofile verified  : True\nresolved status   : active\nowp.repo_read     : delegated -> allowed\nowp.apply_patch   : reserved -> AGENCY_HUMAN_DECISION_REQUIRED\n\n\nYou can also verify existing bundles:\n\nbash\n# For Surface Bundle\nowp surface-verify PATH\n\n# For Acceptance Bundle\nowp acceptance-bundle-verify DIRECTORY\n\n\nMore details on offline verification are available in the official documentation.\n\n## Links\n*   **GitHub Repository**: [https://github.com/dengyier/OpenWorkProof](https://github.com/dengyier/OpenWorkProof)\n*   **PyPI**: [https://pypi.org/project/openworkproof/](https://pypi.org/project/openworkproof/)\n*   **Protocol Documentation**: [https://github.com/dengyier/OpenWorkProof/blob/main/docs/protocol/human-agency-profile-v0.1.md](https://github.com/dengyier/OpenWorkProof/blob/main/docs/protocol/human-agency-profile-v0.1.md)\n*   **Offline Verification Guide**: [https://github.com/dengyier/OpenWorkProof/blob/main/docs/offline-verification.md](https://github.com/dengyier/OpenWorkProof/blob/main/docs/offline-verification.md)","metrics":{"detailViews":0,"githubClicks":0},"dates":{"published":null,"modified":"2026-09-13T11:38:19.000Z"}}