8 projects
agentic-security-harness
Open-source defensive harness and learning lab for reproducing and measuring agentic AI failure modes with portable traces, attack graphs, scorecards, and data-boundary tests.
agentic-llm-router
Cost-aware multi-provider LLM router with role tiers (cheap/mid/chief/audit).
llm-cheap-filter
Deterministic pre-filter + cheap→chief escalation pipeline — send only the few items that matter to your expensive model.
ai-agent-handoff-harness-extension
Optional advisory-only AI Agent Handoff extension for Agentic Security Harness.
ai-agent-handoff
File-based handoff protocol for AI coding agents + a PreToolUse safety guard.
agentic-transfer-verifier
Local verifier for agentic data handoffs: envelope, provenance, trust, authority, identity, capability, and audit checks.
agentic-transfer-verifier-harness-extension
Operator-approved digest-only Harness extension for Transfer Verifier.
llm-safety-playbooks
Data-only defensive playbooks and canonical offline advisory policy pack.
