Skip to content
Preprint

NovaFabric: A Black-Box Recorder for AI Agents with Sealed, Replayable, Diffable and Auditable Runs

Oct 2026 · 0 citations
Computer Science

TL;DR

NovaFabric is described, an open-source (Apache-2.0) black-box recorder for AI agents that turns a run into a sealed, replayable, diffable and auditable evidence capsule.

Abstract

An AI agent run is no longer a function call. It is a cascade of prompts, model calls, tool invocations, file and network effects and sub-agents. When such a run misbehaves, or an auditor asks what happened, logs and traces answer poorly: they are mutable, partial and cannot be re-executed. This technical report describes NovaFabric, an open-source (Apache-2.0) black-box recorder for AI agents that turns a run into a sealed, replayable, diffable and auditable evidence capsule. The design rests on two formats only. The Run Capsule is a directory of flat files and the source of truth; every database is a rebuildable index over capsules. The Evidence Bundle is the signed export for an auditor. Everything else follows existing standards: OpenTelemetry GenAI, OpenLineage, W3C PROV, in-toto/DSSE, RFC 3161 and CycloneDX. A single-node run is the smallest case of a distributed one; the schema supports a capsule hierarchy for Slurm arrays and Kubernetes jobs, though automatic parent finalization is library-only today. The report covers the architecture and the engines behind the verb chain capture, seal, replay, diff and audit: fail-closed mocked replay; a diff gate with a stable exit-code contract; DSSE signatures that bind their intent and a capsule root that commits to file names; a capsule treated as untrusted input; signer identity-trust levels with offline TSA and CRL checking; maker-checker promotion against an operator-held trust list; and a deny-by-default authorization table for every dashboard route. It presents no new experiments; the evaluation is in arXiv:2609.12582. Every count except the private ADR tally is generated by a probe script run on the public source at the v0.107.0 tag (150 top-level commands, 84 Python subpackages, 16,721 test functions), every capability carries an explicit maturity label, and honest-limits boxes state where the system stops.

View source

Similar papers

Preprint Sep 2026

Tracekit: Tamper-Evident Intent-Reasoning-Action Auditing for AI Agents

This work presents Tracekit (open source, MIT, version 1.4.1), which turns each agent run into evidence a third party can check offline, which turns each agent run into evidence a third party can check offline.

Bravish Ghosh · 2 citations
#artificial intelligence Preprint Oct 2026

Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed

AI agents now install packages, call model APIs with their operators'keys and change code in repositories that deploy to production. The network, credentials and write access they need are also how they can leak data, steal a key or change a system nobody approved. Sandboxes contain an agent but leave little evidence o...

Bravish Ghosh · 0 citations
Preprint Oct 2026

Model-as-a-Trojan: Self-Activating Covert DNS Exfiltration Baked Into the Weights of an LLM Agent

Open-weight models are downloaded from public hubs and run inside agent harnesses that grant them tools, most powerfully, a shell, under the assumption that a sandbox contains whatever the model might do. This paper demonstrates that the assumption has a blind spot: the weights themselves can be the malware, and the sa...

Barak Haryati, Shaked Zychlinski · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.