NorviTech — Armiger v3.2.1 (Model Bundle v3.0.0 / v3.0-gold-r5) Neural Torrent & DHT Intelligence

NorviTech develops Armiger, a 9-head byte-level RoPE Transformer (8.30M parameters) with a modular plugin suite for high-throughput classification, safety gating, and canonical title/year extraction on raw BitTorrent and DHT metadata. Library and prebuilt container release v3.2.1 ships with verified model bundle v3.0.0 (v3.0-gold-r5).

Official Model Repositories

• NorviTech/armiger-ultra (Flagship — 32.5 MB FP32 + 15.7 MB INT8 + 6 plugins): FP32/INT8 ONNX, PyTorch checkpoint, 7-tag Viterbi span extractor, and all 6 plugins (SwarmSurvivalNet, SwarmPriors, ZeroCueCatalog, AudioLanguageGuard, CalibrationAndDHT, ArmigerDHTDBSync) behind ArmigerUltraPipeline. 0.21 ms/item batched GPU; 96.86% 6-dimension LOTO (Suite B LOTO N=1,025), 97.01% 11-class (W5A-Test N=703), 91.27% 9-class (R5-Test N=996).
• NorviTech/armiger (CPU edition — 15.7 MB INT8 ONNX): CPU-only (numpy + onnxruntime). 2.44 ms/item single-item (326 items/s batch-64, M4 Pro CPU); 99.90% parity with FP32 (91.16% on R5-Test N=996; 96.85% on Suite B LOTO N=1,025).
• Components (bundled in NorviTech/armiger-ultra): armiger-swarm-survival · armiger-swarm-priors · armiger-zero-cue-catalog · armiger-audio-guard · armiger-calibration-dht · armiger-dht-db-sync

Ready-Made Docker Setups, Packages & Connectors (v3.2.1)

• Core package, prebuilt GHCR containers & evaluation: spencernorton/armiger (v3.2.1) · License: Apache-2.0
  • Bitmagnet + Armiger Ultra: Two-line Docker Compose setup (oci://ghcr.io/spencernorton/armiger-bitmagnet-stack:3.2.1) · Environment-Variable Reference
  • Rats Search + Armiger Ultra: Two-line Docker Compose setup (oci://ghcr.io/spencernorton/armiger-rats-search-stack:3.2.1)
  • Standalone Armiger Ultra HTTP Container: ghcr.io/spencernorton/armiger:3.2.1
• Standalone sidecars for unmodified indexers (v1.1.1): spencernorton/Armiger-Connectors
  • Stock Bitmagnet (bitmagnet-io/bitmagnet): bitmagnet/bitmagnet_connector.py — polls untagged torrents via GraphQL, runs vectorized Armiger inference, prunes .exe/.scr/.lnk malware and honeypot traps, writes armiger-* tags.
  • Stock Rats Search (librats/rats-search): rats-search/rats_search_connector.py — drop-in REST/SQLite sidecar classifier and safety filter.
  • DH-Waypoint processorapi/v1 plugin (spencernorton/DH-Waypoint): dh-waypoint/ — pre-ingest admission (/v1/admit), batch classification (/v1/classify), 4-tier feedback (/v1/feedback).
  • Torznab pre-grab proxy (Prowlarr/Sonarr/Radarr/Lidarr/Readarr): arr-stack/armiger_torznab_proxy.py — filters malware lures, dead swarms, and unrequested foreign-audio releases before grab.
  • Post-import *Arr/qBittorrent webhook: arr-stack/armiger_arr_webhook_receiver.py — ffprobe ground truth for local conformal calibration and opt-in anonymous BEP-44/46 updates.