The Platform
Five packages shipping on PyPI today, one unified install, and a Phase I agentic prototype available under briefing.
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.
$ pip install oubliette-shield 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.
$ pip install oubliette-dungeon 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.
$ pip install oubliette-trap 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.
$ pip install "oubliette-suite[full]" 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.
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.