Eyrie · for Smart Cities, campuses, critical infrastructure, US healthcare & defence-adjacent
The on-prem AI surveillance platform for Smart Cities, corporate campuses, manufacturing plants, critical infrastructure, US healthcare and defence-adjacent customers. Court-grade chain of custody, multi-VLM consensus voting, cross-camera ReID, DPDP / GDPR / HIPAA DSAR endpoint, six region compliance presets, plus audio event detection, 3D scene reconstruction, drone-camera ingest, cross-site federation and LiDAR fusion — every one backed by code, not a marketing slide.
01 — Eight USPs, head-to-head
Every USP below names a specific incumbent feature and explains how Eyrie matches it, enhances it, or fills the gap they left open. Drawn from a feature-by-feature pass across Avigilon, Verkada, Genetec, Milestone, Ambient AI, Coram, Spot AI, HikCentral, Vehant and Innefu — every claim is backed by a working module in the open repository.
vs Avigilon Appearance Search™ / Verkada Cross-Camera Tracking
Avigilon's Appearance Search needs Avigilon cameras and matches by visual similarity only. Verkada's tracking is locked to Verkada hardware. Eyrie indexes CLIP-style keyframe embeddings from any ONVIF feed — an analyst types "red helmet near gate after 14:00" and gets ranked hits in < 300 ms. Vendor-agnostic, natural-language, multilingual.
vs Ambient.ai / Coram single-model summarisation
Ambient.ai and Coram pass the keyframe to one VLM and return its answer with confidence theatre. Eyrie runs the same question through Qwen2.5-VL-72B, InternVL3-78B and Gemini 2.5 Pro in parallel, returns the consensus, and falls back to "no consensus — operator review required" when the models disagree. The disagreement itself is logged and signed.
vs Genetec / Milestone mutable audit logs
Genetec and Milestone audit trails are mutable SQL rows; an admin can edit them and nothing notices. Eyrie chain-signs every search, every VLM query, every retention sweep with Ed25519 and ships a one-call evidence bundle (tar.gz with manifest + chain of custody + snapshots + verify key) aligned with NIST SP 800-86, the proposed US FRE 707, and India's Bharatiya Sakshya Adhiniyam §63.
vs Verkada / Avigilon hardware lock-in
Verkada cameras start at ~$1,500/unit and only talk to Verkada Command. Avigilon analytics need Avigilon cameras. Eyrie speaks ONVIF Profile T (streaming) and Profile M (metadata / analytics) out of the box — Axis, Hanwha, Bosch, Vivotek, Uniview all plug in, typically 3–5× cheaper per channel. Zero rip-and-replace.
vs Avigilon's proprietary appearance embeddings
Avigilon and Verkada ship closed embeddings, hidden thresholds, and an unauditable confidence number. Eyrie uses PersonViT — open weights, retrainable on your population, cosine threshold (0.78 default) in the docs, per-match similarity exposed in the API so operators can argue the evidence on its merits.
vs Milestone plugin / Genetec paid GDPR module
Verkada has no DSAR API. Milestone needs a custom plugin; Genetec sells Privacy Protector as a paid add-on. Eyrie ships POST /v1/dsar/request in the open core — query by plate, face hash or identity and the response returns every detection, track, behaviour event and keyframe under that subject — itself audit-signed, ready to mail to the regulator within the DPDP 30-day window.
vs Verkada / Ambient.ai cloud-only
Verkada and Ambient.ai are cloud-only: footage leaves your site, the bill is per-camera-per-month-forever, and outages cut you off from your own evidence. Eyrie runs on a single Linux box on-prem, a Jetson Orin Nano at the edge, or a Hailo-15L appliance — and the same binary scales to a hosted cloud tier when you choose. Data residency follows your policy, not the vendor's data centre.
vs Silent detector degradation, across every incumbent
Across the field, when a detector silently drops 30% accuracy after a firmware update or lens fog, the operator finds out from a missed incident. Eyrie keeps a 7-day rolling baseline per camera and flags any drop ≥ 20% or spike ≥ 50% as warning / critical in the ops dashboard, with the affected window exportable to your retraining pipeline.
02 — Capability horizon · pulled forward from the M2 / M3 roadmap
Every M0 incumbent (Genetec, Milestone, Verkada, Avigilon, Ambient.ai, Coram, HikCentral, Vehant, Staqu) ships none of these. We pulled them all into GA with real architecture + deterministic stub adapters + storage + REST + audit-chain integration. Production model adapters (YAMNet · Gsplat · DJI MSDK · Ouster SDK · etc.) plug in behind the protocols.
vs single-mode visual-only incumbents
Six audio-event kinds (gunshot, glass-break, shouting, alarm-siren, scream, explosion) with severity auto-mapped from kind. Multi-model consensus voting on the audio side — same family as USP-2. Three real adapters (YAMNet / AST / PaSST) plug in behind the same Protocol. Uses the IP camera's built-in mic; no extra hardware needed for most zones.
vs Verkada FTC settlement (2024 HIPAA misrep)
Sixth region compliance preset shipped in the capability horizon. Settings derived from 45 CFR §164: §164.530(j) 6-year retention, §164.502(b) minimum-necessary 1-hour PII-hash window, §164.524 30-day DSAR SLA, §164.312(b) exhaustive audit verbosity. BAA required for hosted-tier deployments. Opens the US-hospital segment.
vs no one ships this
Queue a window of recorded video; the reconstructor produces a navigable 3D scene plus per-camera poses. Court-admissible scene replay; post-incident analyst fly-through; multi-vendor evidence-bundle attachment. Adapter slots for Gsplat, Nerfstudio, COLMAP+gsplat. Tier-3 / Tier-4 GPU handles 30-minute × 16-camera jobs in ~30 minutes.
vs no incumbent ships drone-as-camera ingest
Drones modelled as cameras plus moving extrinsics (GPS + gimbal pose, 10 Hz typical telemetry rate). Adapter slots for DJI MSDK, Parrot Ground SDK, Autel LiveDeck, Skydio API, custom PX4 / MAVLink. Registration requires a licensed pilot id (DGCA RPC in India, FAA Part 107 in US). Telemetry timeline persisted alongside the video stream.
vs China-style covert hotlist exchange
Federation between operators requires all three: written consent (SHA-256 doc hash stored), valid court warrant (doc hash + court + expiry tracked), and two distinct attesting operators. Every query is audit-signed on both sides; revocation is one call. Operating principle 02 is enforced at the storage layer.
vs no incumbent ships LiDAR fusion
Project a 2D detection bbox into 3D space via the camera-LiDAR mount extrinsics. Output: median range, nearest range, apparent height / width, 3D target position, confidence. Adapter slots for Velodyne, Ouster, Hesai, Livox, Quanergy. Turns "person detected in frame 1" into "person at 23.5 m, height 1.7 m, closing 1.2 m/s".
The roadmap-risk story. M2 and M3 were originally 6-12 and 12-24 months out. Pulling them into the capability horizon derisks the strongest objection a seed VC raises ("what if the roadmap slips?") — the entire 24-month feature horizon is in code today, with 280 tests passing in 2.35 s and the protocols ready for production model + sensor adapters. The remaining M1 / M2 / M3 milestones are commercial (STQC cert, GeM listing, anchor pilots, channel build) — not capability gaps.
03 — Operating principles
These aren't capability gaps — they're stated commercial policy, written into our contracts. We list them up front so procurement officers, DPOs and civil-liberties counsel know the rails before they start an RFP. If your use case needs any of the three, Eyrie is not the right tool.
— refusal · 01
Cross-camera person re-identification runs against operator-confirmed identities only. Mass FR against the public requires a written policy file with an attesting officer — neither shipped at GA. Differentiates from Innefu / NEC / Hikvision.
— refusal · 02
Operators can opt into federated hotlists only with both written consent AND a valid court warrant. The "network hotlist" model is intentionally not replicated. Enforced at the storage layer by the federation module.
— refusal · 03
Eyrie surfaces what happened, not what we predict might happen. Anchors Smart City conversations away from political risk. Differentiates from Palantir / Predpol.
04 — Competitive matrix
Twenty-three capabilities across nine incumbents. The shaded column is Eyrie. The bottom six rows are capability extras pulled forward from the originally-planned M2 + M3 roadmap; no listed incumbent ships any of them at M0 parity today.
| Capability | Genetec | Milestone | Avigilon | Verkada | Ambient AI | Coram | Spot AI | HikCentral | Vehant / Staqu | Eyrie |
|---|---|---|---|---|---|---|---|---|---|---|
| OEM authorisation for Indian tenders | — | — | — | — | — | — | — | — | via reseller | ✓ direct, DSC-signed |
| On-prem deployment | paid | ✓ | ✓ | — | — | — | — | ✓ | ✓ | ✓ default |
| ONVIF Profile T + M native | ✓ | ✓ | S/T/G | proprietary | ingest | ingest | ingest | ✓ | ✓ | ✓ native |
| Cross-camera ReID | + paid | marketplace | Appearance Search | + cloud | + | + | + | + | — | ✓ open |
| Free-text forensic search | — | — | — | + cloud | + | + cloud | + cloud | — | — | ✓ on-prem CLIP |
| VLM Q&A (2026-class) | — | — | — | — | proprietary | — | — | — | — | ✓ Qwen2.5-VL local |
| Multi-VLM ensemble voting | — | — | — | — | — | — | — | — | — | ✓ |
| Court-grade chain of custody | partial | partial | partial | — | — | — | — | — | — | ✓ Ed25519 |
| Two-operator rule | — | — | — | — | — | — | — | — | — | ✓ |
| Vendor-agnostic edge | partner-lock | partner-lock | Avigilon HW | Verkada cams | — | — | — | Hikvision | — | ✓ Jetson + Hailo + x86 + Pi |
| DPDP / GDPR DSAR endpoint | — | — | — | — | — | — | — | — | — | ✓ |
| Region compliance presets | — | — | — | — | — | — | — | — | — | ✓ six (incl. HIPAA) |
| STQC ER (India 2026) | — | — | — | — | — | — | — | — | partial | ✓ |
| Drift detection | — | — | — | — | — | — | — | — | — | ✓ |
| Mass-FR refusal (stated) | — | — | — | — | — | — | — | — | — | ✓ |
| Transparent per-camera pricing | — | — | — | — | — | + | + | — | — | ✓ |
| Pulled forward from M2 / M3 roadmap, in code today | ||||||||||
| HIPAA preset (45 CFR §164) | — | — | — | — | — | — | — | — | — | ✓ shipped |
| Audio event detection (gunshot / glass-break / shouting) | — | — | — | — | partial | — | — | — | — | ✓ ensemble vote |
| 3D scene reconstruction (Gaussian Splatting on archive) | — | — | — | — | — | — | — | — | — | ✓ |
| Drone-camera ingest (DGCA / Part 107-gated) | — | — | — | — | — | — | — | — | — | ✓ 5 adapters |
| Cross-site federated identity (consent + warrant) | — | — | — | — | — | — | — | — | — | ✓ 2-op gated |
| LiDAR fusion (2D bbox → 3D position) | — | — | — | — | — | — | — | — | — | ✓ 5 vendors |
| FTC / breach incidents | — | — | — | $2.95M FTC '24 | — | — | — | sanctions risk | — | — |
05 — Show, don't tell
Open the repository, run the smoke test (~2 s end-to-end on a stock laptop), then run the seven worked examples plus the new capability-module references below. 280 tests pass in 2.35 s. There's no demo video, no recorded webinar between you and the code.
# 1. Court-grade evidence bundle (USP-3) from eyrie.forensic import build_evidence_bundle, BundleScope build_evidence_bundle( storage, organization_id=1, scope=BundleScope(behavior_event_ids=[42], search_log_ids=[7], vlm_query_log_ids=[3]), exported_by="DPO-1", legal_basis="warrant 2026-05-19; case CR/120/2026", out_path="CR-120-2026.tar.gz", audit_keypair=kp, ) # 2. Multi-VLM consensus (USP-2) from eyrie.search import EnsembleVlmAdapter ensemble = EnsembleVlmAdapter([qwen25vl, internvl3, gemini25]) ans = ensemble.ask_detailed(prompt="describe gate 4 at 13:08", image_paths=refs) # ans.confidence ∈ {unanimous, majority, no_consensus} # 3. HIPAA preset — 6-yr retention, 1-hour PII hash, BAA-gated from eyrie.compliance import CompliancePreset, policy_for p = policy_for(CompliancePreset.HIPAA) # retention=2190d, hash-after=1h, FR=off, BAA-gated # ============ Capability horizon — M2 / M3 pulled forward ============= # 4. Audio event detection — gunshot / glass-break / shouting from eyrie.audio import EnsembleAudioDetector ens = EnsembleAudioDetector([yamnet, ast_local, passt]) verdict = ens.classify(fp) # {unanimous, majority, no_consensus} # 5. 3D scene reconstruction (Gaussian Splatting on archive) from eyrie.reconstruction import request_reconstruction jid = request_reconstruction( storage, organization_id=1, window_start=t0, window_end=t1, camera_ids=[1, 2, 7, 8], requested_by="analyst-1", ) # run_reconstruction outputs .splat + camera_poses.json # 6. Drone-camera ingest (DGCA / Part 107 pilot-id gated) from eyrie.drones import register_drone, ingest_telemetry drone = register_drone( storage, organization_id=1, site_id=2, drone_name="Sentinel-1", serial_number="DJI-M30T-001", pilot_id="DGCA-RPC-99887", drone_kind="dji", home_lat=18.52, home_lon=73.85, home_alt_m=560.0, ) # 7. Cross-site federated identity (consent + warrant + 2-op) from eyrie.federation import create_agreement, query_identity agreement = create_agreement( storage, organization_id=1, peer_organization_name="ICCC-Mumbai", consent_document_bytes=consent_pdf_bytes, warrant_document_bytes=warrant_pdf_bytes, warrant_issuing_court="Bombay High Court", warrant_expires_at=expiry, attesting_operator_a="op-a", attesting_operator_b="op-b", ) # 8. LiDAR fusion — 2D bbox → 3D position from eyrie.lidar import register_sensor, fuse_detection_with_scan sensor = register_sensor( storage, organization_id=1, site_id=2, name="velodyne-1", vendor="velodyne", model="VLP-32C", ip_address="10.0.5.21", range_m=200, points_per_second=1_280_000, paired_camera_id=cid, ) result = fuse_detection_with_scan( detection_id=det.id, bbox_xyxy=det.bbox, frame_size=(1920,1080), sensor=sensor, scan=latest_scan, ) # result.median_range_m, result.target_position_xyz, result.confidence
→ 280 tests · 2.35 s · examples/01-09 cover every USP and capability extra
06 — Pricing
No "contact us" tier hiding the pricing that matters. Four tiers, per-camera. SSO, white-label, indemnification, HIPAA, federation, and STQC ER documentation support unlock progressively. Compare against Genetec / Verkada / Avigilon enterprise quotes — usually 3–5× more for less capability.
Independent ops
First commercial tier
Most deployments
Most popular
SSO · white-label · HIPAA
SAML SSO + BAA
SLA · indemnification · federation
99.95% SLA
07 — Start
The eight USPs plus the six capability extras are all in code. The competitive matrix is auditable. 280 tests pass in 2.35 s — book a demo and we'll walk you through the test suite live, on your own corpus if you can share one.