Skip to main content

The Platform

Five packages shipping on PyPI today, one unified install, and a Phase I agentic prototype available under briefing.

AI Firewall
Shipping · PyPI v1.0.1

Oubliette Shield

Five-stage runtime detection pipeline that blocks prompt injection and jailbreak attacks in under 2ms, then deceives attackers with honeypots and honey tokens. 12 LLM providers, 9 SDK integrations.

F1: 0.98<2ms ML12 providers9 SDKsApache 2.0
$ pip install oubliette-shield
Adversarial Testing Engine
Shipping · PyPI v1.0.2

Oubliette Dungeon

Multi-agent red team for AI systems with 72 YAML-defined attack scenarios across 10 categories. Multi-provider comparison, React review dashboard, MCP server, polyglot tool integration.

72 scenariosAISI peer reviewMCP serverReact dashboardApache 2.0
$ pip install oubliette-dungeon
Deception Decoys
Shipping · PyPI v0.2.0

Oubliette Trap

AI-agent deception platform — honeypot MCP servers that attract, contain, and fingerprint autonomous AI agents inside interconnected fake environments. Behavioral classification (LLM, script, human, compromised) with STIX 2.1 / CEF intelligence export.

honeypot MCP serversagent fingerprintingSTIX 2.1 / CEFApache 2.0
$ pip install oubliette-trap
One install, the whole platform
Shipping · PyPI v0.1.0

Oubliette Suite

Umbrella package with a unified CLI: shield + dungeon by default, warden and trap via the full extra. The fastest way to evaluate the platform end to end.

unified CLIshield + dungeon[full] extraApache 2.0
$ pip install "oubliette-suite[full]"
Multi-agent framework
Phase I prototype · briefing on request

Agentic Cyber Defense

Four-agent framework (Project Management, Code Generation, Cyber Analysis, Vulnerability Research) with a human-on-the-loop operator interface. CALDERA-emulated; every autonomous action gated by the five-stage safety pipeline; citation-bound vulnerability research.

4 agents + UIATT&CK-alignedCALDERA substratesafety-gatedaudit-replayable

How the pieces fit

Each capability is independently useful. They reinforce each other when deployed together.

Shield ↔ Dungeon

Dungeon attacks your AI under controlled scenarios. Shield defends. Measure the detection rate. Close the gaps. Repeat.

Agentic ↔ Shield

Shield's five-stage pipeline is the safety substrate for every autonomous tool emission in the agentic framework. No black-box autonomy.

Agentic ↔ AI RMF

The agentic framework's evidence-integrity pattern binds every vulnerability claim to a retrieved corpus record — citations grounded, not synthesized. Aligned with NIST AI RMF GOVERN / MAP / MEASURE / MANAGE controls.

Dungeon ↔ AISI inspect_evals

Dungeon scenarios are contributed back to UK AISI's inspect_evals (PR #1358, 35 scenarios under review) for third-party methodology validation.