GRAFOMEM CGR Read

Enables agents to locally validate and decode transparency-log receipts against a chosen trust root, checking exact payload inclusion, grant admission, and receipt contents without a backend, account, key, or network. It also reports sealing, split-view, append-authority, and attribution outcomes using read-only tools.

Provides read-only access to CWI's trust infrastructure, enabling Gear Ledger provenance queries, agent trust scoring via the Verdict Engine, and NEEDLE DROP ledger hash-chain verification over stdio.

Lets an assistant read recorded production AI agent runs — steps, model and tool calls with arguments, and outcomes — along with the findings of comparison runs that checked a prompt or model change against those recordings, and verify a signed evidence bundle offline with no account or network. It is strictly read-only: no tool starts a replay or comparison, so nothing can spend money or act without a person deciding.

Enables querying and verifying signed receipts of static inspections of public agent skills via read-only tools such as search_receipts, get_receipt, and get_verification_material.