In Toto Python Packages

ai-rulez

Standards-compliant lifecycle tool for agent knowledge and capabilities: author, generate, bundle, validate, govern, publish.

agent-evidence-vectors

Conformance corpora and reference verifiers for AI-agent and supply-chain evidence formats

agtmls

Signed, audited registry of agent skills (SKILL.md) for Claude Code, OpenAI Codex, Aider and Antigravity: verified installs, a prompt-injection and supply-chain audit with SARIF, a signed index, signed in-toto attestations, and with/without evals that measure whether a skill helps. Stdlib-only Python CLI, agtmls-spec L5.

novafabric

Open-source replay and evidence infrastructure for AI agents. Capture runs as portable Run Capsules for replay, diff, lineage, provenance, and audit.

warrant-cli

Humans state intent. Agents write the code. Evidence decides what ships. An open protocol and reference CLI for agent-built software that humans direct without reading the code.

emet

Witness verification. Byte-integrity witness for AI source/view consistency. Shipped v1.1.0. Advisory-only verdict lattice. MPL-2.0.

rung-ai

Did your AI agent run what it says it verified, or only claim it did?

agent-evidence-admission

OPA, Kyverno and Sigstore policy-controller rules that admit signed AI-agent execution evidence against a consumer-pinned policy.

context-report

An open, signed report format for whether an agent plugin, hook, skill, or AGENTS.md actually works.

provetrail

An open standard for verifiable execution provenance: a portable, third-party-verifiable record of what an agent did, in what order, and under what governance.