GitHub Repository

Agenda Intelligence — product runtime + evidence-discipline layer for strategic intelligence agents. Four surfaces (MCP, HTTP, A2A, Cloudflare Worker) over one core service layer. Ships one live vertical worker: Middle Corridor Deal Risk Gate. Schema-validated I/O, evidence audit, geography routing. No live retrieval, no factual verification.

3 starsPython

Agenda Intel MD – schemas and CLI to audit LLM strategic-risk briefs

Name: Agenda Intel MD – schemas and CLI to audit LLM strategic-risk briefs
Availability: InStock
Author: vassilbek

by vassilbek·May 16, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●SolidNiche GemBig Brain

Schema-valid evidence packs for AI agents when generic evals miss domain nuance.

Strengths

•Claim-level provenance tags (primary, inference, judgment) enforce strict evidence discipline.
•Stdio MCP server integration allows agents to self-correct during generation loops.
•Signal lifecycle tracker schema handles evolving geopolitical situations over time.

Weaknesses

•Extremely narrow audience; irrelevant for general-purpose application developers.
•Relies on human-defined rubrics rather than automated fact-checking against live data.