Receipts Python Packages

amazon-orders

A Python library (and CLI) for Amazon order history, line items, and transactions

hydracept

Execution infrastructure for AI agents. Run text, reasoning, image, audio, video, 3D, domains, DNS, and more through one capability API—with durable jobs, transparent pricing, receipts, budgets, and BYOK.

treeship-sdk

Portable trust receipts for agent workflows. Signed, chained, verifiable.

agent-passport-system

Python SDK for Agent Passport System identity, scoped delegation and signed receipts.

agent-security-harness

AI agent security harness, adversarial testing: 640 executable tests in the v4.26.1 release, across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loop, skill supply chain. Four target shapes: a verdict must be able to be wrong AND to be right. OWASP Agentic v1.1 T1-T17, AIUC-1 19/20 (2026-Q1/Q2 set), NIST AI 800-2.

treeship-commerce

Portable trust receipts for agent workflows. Signed, chained, verifiable.

proofbundle

Portable evidence for AI work, verifiable offline. Integrity, not truth

continuity-receipt

Open spec + reference verifier for continuity receipts: signed, offline-verifiable records of governed AI-agent tasks (decision, authority, execution, delivery, termination, settlement).

tersign

Python SDK for Tersign, the evidence layer for the agent economy — offline verification of counter-signed receipts, hash chains, chain commitments and frozen evidence bundles. Zero dependencies, standard library only. PyPI: tersign

aqta-verify-receipt

Open specification and reference verifiers for Seal records: ATTESTATION-v1 for AI model-call decisions, ACTION-v1 for agent actions. Ed25519, canonical JSON, checked offline against a published key.

invoicedataextraction-sdk

Official Python SDK for Invoice Data Extraction. Uploads your files, submits the extraction, waits for it to finish and hands you the rows as data, or a spreadsheet, in a few lines of code.

yapitalism

Drive terminal coding agents by voice, with receipts that never claim more than they proved

szl-receipt-dsse

Shared signed-receipt library — DSSE/ECDSA-P256, cosign-compatible, UNSIGNED-honest fallback. The one signing primitive every SZL component shares.

kptncook

Fetch receipts from kptncook API and export them to mealie or paprika

szl-guardrail-receipt

Wrap any LLM guardrail (Llama-Guard / NeMo / guardrails-ai / your callable) and emit a signed, hash-chained DSSE decision receipt — aligned with governed-receipt-spec. UNSIGNED-honest fallback; never fabricates a signature, energy joule, or a Λ 'proven'.

szl-energy-attest

Attestable energy receipts for governed compute — MEASURED-NVML joules (or honest UNAVAILABLE null), cheapest-watt placement, hash-chained signable receipts. Vendors szl_energy_core. Λ = Conjecture 1 (advisory) · never fabricates a joule · Mirrors HF SZLHOLDINGS/szl-energy-attest · Apache-2.0.

agent-receipts

Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.

whitemagic-mcp

Local-first, governed memory and session continuity for AI coding agents, over MCP - verifiable handoffs via signed continuity receipts. Rust, MIT, no telemetry by default.

coherence-membrane

Give AI agents inspectable observations of files, images, screens, and context with receipt-backed perception.

langchain-fairseal

Provably fair selections — commit before outcome, drand entropy, Merkle receipts anchored on Base. For games and AI agents.

nobulex

Reproducible research on verification boundaries, plus the earlier Nobulex receipt prototype. Current financial decision-integrity gateway: github.com/arian-gogani/nobulex-registry.

delhaize-mcp

Unofficial MCP server to fetch your own Delhaize (Belgium) till receipts and weekly promotions with a headless browser. No password handling.

proof-of-edition

Proof of Edition: verify that an inference API serves the model edition it claims. Signed manifests and receipts, a transparency-logged registry, re-execution audits and the watch.

obsigna

Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.