agent-audit-ledger is a dependency-free Python package for auditing AI agents. It verifies append-only ledgers, probes sandbox network egress, and checks whether approvals produce their intended effects for developers building accountable autonomous systems.
agent-audit-ledger is an AI security & guardrails project. It focuses on verifying AI-agent records, network restrictions, and approval effects without relying on external dependencies. It is built as an open-source project for AI agent developers and security engineers. The project is open source (MIT). It runs on the command line, and it can be self-hosted.
agent-audit-ledger first shipped in 2026. Among its 7 catalogued features are ledger verification, append-only records, and tamper detection.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do