You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Postgres extension that emits audit-stream-py-compatible governance events on watched table CRUD via pg_notify, plus a Python LISTEN bridge daemon. The database-tier governance producer for the Kinetic Gain Protocol Suite.
FastAPI service that drafts AI Procurement Decision Cards (Kinetic Gain Protocol Suite spec #11) from a buyer rubric and vendor Suite documents. First cross-ecosystem bridge: Suite x Decision Intelligence.
Command-line tool for the AEO Protocol v0.1. Validate, fetch, inspect, and extract claims from AEO declaration documents. Built on aeo-sdk-rust. clap + ureq + colored. Cargo-installable.
Runtime permission broker for MCP tool invocations. Composes AI Procurement Decision Cards into PolicyBundles, applies deny-trumps-allow rules at request time, emits tamper-evident audit-stream events. The runtime enforcement point of the Kinetic Gain Protocol Suite.
Agent Cards v0.1 draft. Declarative JSON document disclosing an AI agent's capability surface, refusal behavior, evaluations, and deployment posture. Like HuggingFace model cards, but for agents. Part of the Kinetic Gain Protocol Suite.
AI Evidence Format v0.1 draft. JSON document format for structured citations that travel with LLM-generated claims: source identity, span selector, retrieval confidence, freshness, content hash, declared synthesis role. Part of the Kinetic Gain Protocol Suite.
Open JSON spec for student-side AI disclosure attached to submitted work. The student-side counterpart to AI Tutor Cards. Part of the Kinetic Gain Protocol Suite.
Open 30-attack prompt-injection corpus + Python harness with Agent Card refusal-taxonomy back-references. 10 attack categories, 4-level severity, 5 scoring methods. Pairs with the Kinetic Gain Protocol Suite.
Visual web harness for prompt-injection-bench. Paste a JSONL transcript, see a procurement-grade pass-rate report. Live at bench.kineticgain.com. Client-side React + TS.
BFS crawler for AEO Protocol v0.1 declaration graphs. Seed an origin, follow primary_source URIs, emit JSON Lines records of every fetch. Built on aeo-sdk-go. Concurrent, depth-limited, budget-capped, stdlib-only HTTP.
AI Tutor Cards v0.1 draft. Disclosure spec for AI agents in an educational role: audience (age, grade, subjects), pedagogy (Socratic / homework_policy / assessment_policy), safety & privacy (FERPA / COPPA / mandated-reporter). Sixth spec in the Kinetic Gain Protocol Suite.
Open JSON spec for vendor disclosure of AI systems used in healthcare. HIPAA / FDA / SaMD posture, bias audits, EHR integration. The HealthTech vertical extension to the Kinetic Gain Protocol Suite. v0.1 draft.
The crawl + aggregate engine behind the AI Procurement Pulse. Probes a universe of vendor domains for the 11 Kinetic Gain Protocol Suite documents and produces the quarterly issue dataset. Issue #1: the zero baseline.
MCP server exposing AEO Protocol declarations as four tools (fetch, inspect, get_claim, well_known_url). Drop-in for Claude Desktop, Cursor, or any MCP-compatible agent. Ships with conforming MCP Tool Cards for every tool. Part of the Kinetic Gain Protocol Suite.
Swift SDK for the AEO Protocol v0.1. Parse, build, validate, and fetch AEO declaration documents. Foundation-only, async/await fetchWellKnown via URLSession. Completes the AEO SDK family at five languages.