Back to browse
GitHub Repository

Deterministic evidence-packet linter for claim-backed AI output. Checks source references, quotes, lexical support, and unmatched numbers before human review; not a factuality verifier.

6 starsPython

Agenda Intelligence MD – evidence-discipline MCP layer for agents

by vassilbek·May 22, 2026·2 points·0 comments

AI Analysis

●●SolidNiche GemBig Brain

Evidence-discipline layer for agents solving hallucination in geopolitical risk analysis.

Strengths
  • Enforces strict schema validation and evidence auditing before generating strategic memos.
  • Includes a heuristic scoring system for decision-readiness based on source quality.
  • Provides a live A2A wrapper on Cloudflare Workers for easy agent discovery and routing.
Weaknesses
  • Highly niche focus on geopolitical risk limits broader adoption beyond specific enterprise use cases.
  • Requires host model to handle final completion, adding complexity to the integration chain.
Category
Target Audience

AI engineers building agents, Risk analysts

Similar To

LangChain · LlamaIndex

Similar Projects