The Auditable AI Ecosystem

Open-source infrastructure for auditing AI agents, from before deployment to after a run.

Eleven open artifacts, each answering one question an auditor asks at one point in an agent's life. The record they produce has two uses: it shows what a system did wrong, and it shows what it never needed to do. Every one is public and citable, and the tools install from PyPI. The stack supports Auditable AI, the company building the auditable layer for AI agents.

This page covers the auditing-of-action arm of the lab's work and says where each piece applies. The research argument behind it is on the home page. For the detection-in-data arm, see PyOD. For the sourced adoption record across every project, see open source.

Start Here

pip install auditable

The fastest way in. auditable is the production entry point, and it sits at the post-run end of the lifecycle below. If you would rather read first, the Auditable Agents framework paper is the shortest path to why the pieces are split this way.

Tool page  |  Docs  |  GitHub  |  PyPI

Where Each Piece Applies

An agent can be checked at three moments, and the evidence available differs at each. Before a run you have the declared configuration and the code. During a run you have the call about to fire. After a run you have whatever the trace preserved. Each artifact below sits at the moment where its evidence exists, and appears once.

Pre · Before Deployment
Does this agent ask for more than it needs? A static scan of agent code for security and over-privilege issues, run before anything ships.
FORTIS Benchmark
Does the agent stay inside the skill it was given? A benchmark for over-privilege in agent skills: whether a model selects the minimally sufficient skill and runs it without expanding into broader tools or actions.
Live · While Running
Aegis Tool
Can this call be stopped before it fires? A pre-execution firewall that gates each tool call while the agent is running.
Is one user's data reaching another? Measures leakage across users in agents that share state.
How much memory leaks between agents? Memory leakage in multi-agent LLM systems, measured against the topology that connects them.
Post · After a Run
auditable Tool
What did this decision rely on, and can it be undone? A framework-agnostic system of record that captures each decision's dependencies, replays them against live state, and rolls back the committed action when they no longer hold.
GRADE Method
Which step went wrong? The research engine auditable is built on: a typed two-layer graph of agent execution and dependency that predicts run failure and localizes the faulting step in a failed multi-agent run.
Who caused this, when the logs are gone? Recovers segment-level attribution in a multi-agent run from the final text alone.

Across the Whole Lifecycle

Three artifacts do not sit at one moment. One says what auditability requires, one measures whether the requirement was met, and one maps the surrounding literature.

Framework
What does auditability actually require? Five dimensions and three mechanism classes: detect, enforce, recover. The grid above is that framework instantiated.
Benchmark
Was the failure catchable at all? Puts one auditor's question to all three information states under a single interface. It scores 72 entrants over 1187 declared configurations and 1162 recorded runs, and publishes the 71 contrasts that fail to separate rather than ranking them.
Reference
Who else is working on this? A curated map of papers, tools, datasets, and standards for reliable, auditable AI agents, with published checks for paper-title and destination consistency.

Build on It

Every artifact here is public, citable, and built to be extended. If you are adding a detector, a policy, or a new lifecycle stage, open an issue on the repository it belongs to. If you are benchmarking against this work, CatchBench is the entrant interface, and it takes submissions that fail to separate as readily as ones that win.

For the company building on top of this stack, visit Auditable AI (auditable.run). Most of this stack lives under github.com/yzhao062. agent-audit and Aegis are maintained in their authors' own repositories, linked from their pages above.