#provenance

Agent Tool Protocol

provin — data provenance-chain implementation of the dPLaaX protocol: cmd/network control plane + cmd/pipeline data plane (Go, ConnectRPC, Ed25519 wireauth, did:dplaax)

Verifiable knowledge graph for scientific experiments

Provenance-aware memory for AI agents.

MCP server for PayPerByte — pay-per-call USDC data feeds for AI agents (x402 on Base; EIP-712 attestations). No API keys, no token.

A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.

Open .skill Protocol - a sealed, inspectable package format for AI agent skills. Reference implementation: skillerr.

This is the boltzmann sdk in python to be used when interacting with the protocol

Compressed Atomic Verb Expressions

RSS for state. Open portable evidence layer for machine state - preserving what an agent or system saw, produced, derived and learned, so another party or future agent can verify the lineage independently.

Causalontology - the world's first programming-language-neutral standard and shared commons for reified causation. AGI's Missing Link.

Trust what you ship: download and verify browser extension artifacts (zip structure, manifest, metadata) and emit a deterministic JSON report for CI release gates.

Hachure — an open trust format. Specification, normative schemas, and conformance test vectors. npm: hachure

Give AI proven facts — a cryptographically verified truth layer for agent AI, built on ZK proofs, selective disclosure, and on-chain provenance.

A runtime where decision models propose and your code decides: typed questions, hard rules, quotes checked against the text, escalation with a guaranteed error budget, replayable traces. Works with any System One model.

The verifiable trail of agent actions — signed, tamper-evident execution receipts for AI agents (MCP & A2A).

No repository description published.

No repository description published.

🐣 Create and set up new npm packages w/ trusted (OIDC) publishing - for one package or a whole monorepo

A verifiable memory layer for language models — facts in a graph, every claim with its source.

Conformance vector suite and reference verifier for the adversarial-execution-evidence in-toto predicate

Spor — a shared memory substrate for teams and agents. Decisions, their reasons, and the traces they leave.

Know what you're letting in — scans, signs and verifies what an agent loads. Agent Skills vs the OWASP Agentic Skills Top 10, with SARIF output and a load-time gate.

Cryptographic trust infrastructure for MCP servers — signed manifests, TOFU pinning, two-gate enforcement, and the "npm audit" scanner.

Local-first Go library for immutable forensic evidence, provenance, and reproducible artifacts.

Guardrails for AI agents, with a receipt. Blocks destructive tool calls before they run and signs every decision into a hash-chained record anyone can verify with an open-source tool.

Verifier for C2PA Content Credentials in pure PHP: JPEG, PNG, WebP and ISOBMFF, with c2patool's verdict. Read and verify only; no signing, no keys, no network.