#audit-trail

Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.

Accordo — agent-native CRM framework for Claude Code, Codex and Gemini CLI. Author custom CRM and Customer Hub source with deterministic workflows, human approvals, audit and trace. Smart CRM is policy-governed; CDP + CRM adds bounded imports and logical identity, with no streaming ingestion, audience segmentation or CDP activation.

The dev team that works while you're away. It asks before it builds, and writes down who decided what.

AgentTrail is a local-first AI agent layer for Ollama/local models that shows its work: semantic search, diff-safe edits, receipts, replay, memory, MCP, reports, and trust controls.

Evidence-backed scientific AI report infrastructure

Asqav extension for the pi coding agent. Block out of mandate tool calls at sign time and keep a verifiable record.

Cross-agent security & quality hardening engine for Claude Code, Codex, and Gemini CLI. Enforces user-authored playbooks, verifiable evidence gates, and auditable readiness reports.

Auditable, contract-driven AI coding agent powered by ICODE-SKILL — fail-closed workflow gates and independently verifiable evidence.

A governance and policy layer that wraps Claude Code with review gates, audit trails, and plain-English rules for multi-agent engineering.

Put risky Claude Code and Codex actions back in front of a human — local-first approval gates, secret redaction, and replayable audit trails.

RSK's harness for agent models: AI does admin work, an independent reviewer checks it, and a human approves anything involving money or a client. Nothing can skip that last step.

Replayable agent evidence, conflict-safe memory, and source-bound multi-agent research on flop.

Retail exception detection and task reliability engine connecting ERP, WMS, and HRMS with deterministic reconciliation, idempotent task workflows, and guardrailed AI advisory.

GitHub Action + CLI for replayable CI/PR/release gate decisions - zero-config Self-Test turning checks, scanners, and AI-agent signals into deterministic, tamper-evident PASS/WARN/BLOCK records. Read-only, zero dependencies, Apache-2.0.