IETF Draft Analyzer v0.1.0 — track, categorize, and rate AI/agent drafts

Python CLI tool that fetches AI/agent-related Internet-Drafts from the IETF
Datatracker, rates them using Claude, generates embeddings via Ollama for
similarity/clustering, and produces markdown reports.

Features:
- Fetch drafts by keyword from Datatracker API with full text download
- Batch analysis with Claude (token-optimized, responses cached in SQLite)
- Embedding-based similarity search and overlap cluster detection
- Reports: overview, landscape by category, overlap clusters, weekly digest
- SQLite with FTS5 for full-text search across 260 tracked drafts

Initial analysis of 260 drafts reveals OAuth agent auth (13 drafts) and
agent gateway/collaboration (10 drafts) as the most crowded clusters,
while AI safety/alignment is underserved with the highest quality scores.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/ietf_analyzer/models.py

@@ -0,0 +1,72 @@
+"""Data models for drafts, ratings, and categories."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from datetime import datetime
+
+
+@dataclass
+class Draft:
+    name: str  # e.g. "draft-zheng-dispatch-agent-identity-management"
+    rev: str  # e.g. "00"
+    title: str
+    abstract: str
+    time: str  # ISO datetime from API
+    dt_id: int | None = None  # Datatracker document ID
+    pages: int | None = None
+    words: int | None = None
+    group: str | None = None  # Working group name (resolved)
+    group_uri: str | None = None  # Raw API URI
+    expires: str | None = None
+    ad: str | None = None  # Area director URI
+    shepherd: str | None = None
+    states: list[str] = field(default_factory=list)
+    full_text: str | None = None
+    categories: list[str] = field(default_factory=list)
+    tags: list[str] = field(default_factory=list)
+    fetched_at: str | None = None
+
+    @property
+    def text_url(self) -> str:
+        return f"https://www.ietf.org/archive/id/{self.name}-{self.rev}.txt"
+
+    @property
+    def datatracker_url(self) -> str:
+        return f"https://datatracker.ietf.org/doc/{self.name}/"
+
+    @property
+    def date(self) -> str:
+        """Return just the date portion of time."""
+        if self.time:
+            return self.time[:10]
+        return ""
+
+
+@dataclass
+class Rating:
+    draft_name: str
+    novelty: int  # 1-5
+    maturity: int  # 1-5
+    overlap: int  # 1-5 (5 = highly overlapping with others)
+    momentum: int  # 1-5
+    relevance: int  # 1-5
+    summary: str  # 2-4 sentence AI summary
+    novelty_note: str = ""
+    maturity_note: str = ""
+    overlap_note: str = ""
+    momentum_note: str = ""
+    relevance_note: str = ""
+    categories: list[str] = field(default_factory=list)
+    rated_at: str | None = None
+
+    @property
+    def composite_score(self) -> float:
+        """Weighted composite: novelty and relevance matter most."""
+        return (
+            self.novelty * 0.30
+            + self.relevance * 0.25
+            + self.maturity * 0.20
+            + self.momentum * 0.15
+            + (6 - self.overlap) * 0.10  # Invert: less overlap = better
+        )