Prebuilt sharp for use with Linux (glibc) ppc64

An automatic, tamper-evident log of your AI's decisions — every model and tool call is recorded and can be verified offline; change any past entry and the check fails.

Compliance and audit-evidence layer for AI agents. Pre-flight checks return allow, block, or hold before a risky action runs, and every decision produces an Ed25519-signed evidence record that anyone can verify offline with the published public key and op

AI work audit receipts — verifies and records what an AI coding agent actually changed in your local git tree. Provides git-based evidence for compliance review (not a compliance guarantee).

AI-powered security incident report generator / AI 自動產生資安事件報告

This repository contains a growing set of Compliance Policies to validate your infrastructure using Pulumi's Crossguard Policy-as-Code framework.

Core library for the 51Degrees Pipeline API

WasmAgent Compliance Engine — TaskSpec-driven verification, local repair, and evidence export for LLM agent runs.

This is a JavaScript source for Evidence. It allows you to run arbitrary JavaScript code as a data source. It's a quick way to get data into Evidence without having to create a new connector.

Extracts OSS license information of the npm packages in your rollup or vite output

Deterministic, framework-independent Factory event replay.

Optional TypeScript-Go semantic refinement sidecar for Fallow

Offline verification and local evidence capture for OpenSoyce signed evidence packets. Verification confirms integrity and origin only.

ISO 27001 compliance workspace for Claude — controls, risks, policies, evidence, audits, and SoA in one local encrypted MCP server

JavaScript obfuscator

Scanner-neutral vulnerability normalization, policy gates, host inventory, and audit-ready evidence for AbsoluteJS applications.

Manages OFAC compliance checks for wallet addresses

Compliance tests for JS libp2p interfaces

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — execution trees, TraceContract checks, Evidence v2, and read-only MCP

Process transparency for agentic work.