LITEHOUSE · LENDING OPERATING SYSTEM

The lending
operating system.

Litehouse is an AI-native, open-source, on-premise operating system for India's small and mid-tier housing finance companies and non-bank lenders. It runs three production agents — Aryabhatta-Analytics, Aryabhatta-CAM, and Aryabhatta-Legal — on the lender's own infrastructure, under the lender's own board-approved AI policy, with an immutable audit lineage that survives an NHB IT inspection by construction.

Litehouse is not a SaaS. It is a software stack you install, a corpus you own, and a runtime you operate.

Read the architecture
01 · WHY AN OS

Why an operating system,
not software.

The horizontal AI vendors are building applications. Applications sit on top of someone else's data, someone else's model, someone else's compliance posture. For the chairman of a ₹400 Cr HFC who watched IL&FS unwind in September 2018 and DHFL in 2019, the question is not "will this AI work?" — it is

"who controls it when the regulator walks in?"

Litehouse answers that question architecturally. The model weights live on your hardware. The borrower data never leaves your perimeter. The audit log is yours. The board policy is yours. The Consent Manager integration is yours. We ship the operating system; you operate it.

03 · COMPLIANCE

Compliance, by construction.

A horizontal cloud-LLM stack achieves FREE-AI compliance by adding controls retroactively. Litehouse achieves compliance because its architecture is the controls. On-prem + open-weight + immutable audit + HITL + board-policy-on-install — the regulator's "show me your AI inventory and your model risk management" question is answered on the day of inspection, not 14 weeks before it.

REGULATION
RBI FREE-AI · Aug 2025

All seven sutras, all six pillars. Board-approved AI policy template ships with the deploy package.

REGULATION
DPDP Act 2023 + Rules 2025

On-prem deployment trivially satisfies cross-border transfer restrictions; Consent Manager integration scaffolded.

REGULATION
NHB IT inspection

AI inventory, model registry, change log, access trail — the four documents the inspector asks for — emitted by the runtime.

REGULATION
SARFAESI 2002

Section 13(2) and 13(4) drafting templates, vetted by the Aryabhatta-Legal corpus.

REGULATION
NI Act Section 138

Cheque-bounce notice generation aligned to Sanjabij Tari v. Kishore S. Borcar (2025) procedural directions and Damodar S. Prabhu compounding guidelines.

REGULATION
RBI IRACP 2025

Borrower-wise NPA + ECL Stage 1/2/3 with dual-auth governance — MCV is the structural primitive.

04 · CORPUS · CAM

Forty-eight profiles.

In an affordable HFC underwriting a tailor in Virar with no GST, no salary slip, and a one-room kirana downstairs — the bottleneck is not the math. It is the surrogate-income reasoning. Aryabhatta-CAM ships with the recipe for every informal-income household in semi-urban India.

01Auto-rickshaw owner-operator
02Auto-rickshaw fleet owner
03Kirana shop (urban)
04Kirana shop (semi-urban)
05Street food vendor (hawker)
06Street food vendor (cart-licensed)
07Kabariwallah
08Dairy (1–5 cattle)
09Dairy (6+ cattle, FPO-linked)
10Weaver (handloom)
11Weaver (powerloom)
12Tailor (home-based)
13Tailor (shop-front)
14Coaching tutor (home)
15Coaching tutor (institutional)
16Gig delivery (single-app)
17Gig delivery (multi-app)
18Salon owner-operator
19Beauty parlour (home)
20Mobile recharge / agent
21Tea stall
22Sweet shop
23Vegetable wholesaler
24Vegetable retailer
25Auto-mechanic
26Tyre puncture shop
27Welding workshop
28Carpenter (job-work)
29Carpenter (own-shop)
30Plumber
31Electrician
32Mason / contractor (small)
33Tempo / mini-truck
34Inter-city truck
35School van operator
36Photo studio
37Print shop
38Photocopy / DTP
39Hardware shop
40Paint shop
41Sanitaryware shop
42Saree / cloth shop
43Footwear shop
44Stationery shop
45Medical shop (rural)
46Pathology lab agent
47Insurance / MF agent
48Real estate broker (small)
05 · ARCHITECTURE

Five commitments.

MCP-native. Hybrid rule + LLM. Human-in-the-loop. Air-gappable. Open-weight. Five non-negotiables that decide what we ship and what we refuse to.

  1. 01
    MCP-native
    Built on Model Context Protocol (Linux Foundation AAIF). Vendor-neutral, governed, open-standard agent fabric. Every connector is portable.
  2. 02
    Hybrid rule + LLM
    Determinism first, intelligence second. Numeric aggregations, regulatory checks, date arithmetic are deterministic. LLM for reasoning, narrative, translation.
  3. 03
    Human-in-the-loop, by default
    Every action with regulatory weight routes to a human approver. Configured per board-approved AI policy. The agent owns the draft; the human owns the decision.
  4. 04
    Air-gappable
    Three deployment modes — fully on-prem, sovereign Indian cloud, public cloud in private VPC. No telemetry leaves perimeter without approval.
  5. 05
    Open-weight
    Model registry ships with audited, production-grade open-weight models — Qwen 3, Llama 3.3, Qwen 2.5 Coder, Mistral Small. Lender pins specific weight hash. No closed-API dependency.
INDIAN LAYER
Surya OCR

Open-source. Strong on Devanagari, Tamil, Kannada, Bengali, Gujarati, Marathi, Punjabi, Malayalam.

INDIAN LAYER
Microsoft Presidio + IN

Built-in PAN, Aadhaar recognisers; custom IFSC, GSTIN. PII redaction & pseudonymisation by default.

INDIAN LAYER
Indian legal corpus

SARFAESI · NI Act · RERA · ToP · state stamp acts · SC/HC precedents (Mardia, Transcore, Celir LLP, Sanjabij Tari).

06 · OPEN SOURCE

The code is free.

The expertise is paid.

Apache 2.0 (model registry components governed by underlying open-weight model licenses). Repo at github.com/aryabhattalabs/litehouse. The MongoDB / HashiCorp / Elastic / GitLab / Confluent playbook, adapted for Indian lending.

TIER
Community
₹0
TIER
Supported
~₹20L
TIER
Managed
~₹50L
TIER
Enterprise
~₹1.2 Cr

Full Litehouse runtime · all 3 agents · MCP fabric · deployment scripts · Discord/Slack support.

BUYER
Developer / curious chairman / RegTech tinkerer

Community + named SLAs (Sev-1 < 4hr) · private support channel · monthly office hours · security advisory feed.

BUYER
Small HFC · ₹100–500 Cr AUM

Supported + remote operations · model upgrade management · on-call DevOps · FREE-AI evidence pack management.

BUYER
Mid HFC / NBFC · ₹500–2,000 Cr AUM

Managed + dedicated solutions engineer · custom-corpus extensions · NHB-inspection accompaniment.

BUYER
Mid / Large HFC · ₹2,000–10,000 Cr AUM

PRICING ILLUSTRATIVE · LITEHOUSE PRE-SEED PROJECTION

07 · TCO

The four-option
table.

For a ₹500 Cr AUM HFC, over three years.

Litehouse Managed is 78% cheaper than the horizontal vendor stack over three years for the same AUM bucket — and architecturally delivers what the horizontal stack cannot: sovereignty, FREE-AI compliance, and the 48-profile corpus.

OPTION3-YR TCOWHAT YOU GETWHAT YOU DON'T
Status quo₹3.6 CrManual analyst desk + outsourced legal + cloud-vendor BI. Familiar workflow.No AI leverage; FREE-AI gap; analyst attrition; Sec 138 windows missed.
Horizontal AI vendor~₹2.4 CrChat layer on top of existing data; cloud-LLM dependency.Cross-border data exposure (DPDP friction); no Indian credit ontology; no 48-profile corpus.
Litehouse Managed ★~₹1.5 CrThree production agents · on-prem · FREE-AI by construction · remote ops included.Lender hosts hardware (one-time RTX 6000 Ada: ~₹40L).
Litehouse Enterprise~₹3.6 CrManaged + custom corpus + regulator liaison + NHB-inspection accompaniment.Highest sticker; reserved for >₹2,000 Cr AUM.
Litehouse pre-seed projection
08 · PILOT

The Agrim pilot.

Reference, not revenue. Proof of architecture, not proof of scale.

Agrim Housing Finance Pvt Ltd. Incorporated December 2018, registered with NHB. AUM growth documented by CARE Ratings: ₹117 Cr (Mar 2023) → ₹285 Cr (Mar 2024) → ₹314 Cr (Jun 2024). Co-lending partners: Godrej Housing, Singularity Creditworld, Vastu, DMI, Gosree. Fintech Startup of the Year, IFTA 2023. Home/Mortgage Lender of the Year, India Credit Risk Management Summit 2024.

Wk 1–2
Phase 0

Architecture lock; RTX 6000 Ada delivered; Litehouse v0.9 installed; board-policy template adopted.

Wk 3–6
Phase 1

Aryabhatta-Analytics live. Replaces 80% of analyst SQL queries. Baseline TAT measured.

Wk 7–12
Phase 2

Aryabhatta-CAM (10 of 48 profiles in production). Underwriter time saved measured.

Wk 13–17
Phase 3

Aryabhatta-Legal: title vetting + Section 13(2) drafting in production. NHB-inspection-ready audit log validated.

Wk 18–20
Phase 4

FREE-AI evidence pack. Board-policy + AI inventory + DPIA + algorithmic-audit kit.

As of Q1 FY27, the Agrim pilot is starting, not completed.
09 · DEPLOY

A guide for the head of IT.

A single RTX 6000 Ada workstation amortised over 4 years costs the lender less than 6 months of a horizontal AI vendor's SaaS subscription — and the lender owns the asset, the model weights, and the borrower data lineage at the end.

TIERHARDWARECAPEXOPEX / YRFITS
Workstation1× RTX 6000 Ada (48GB) · 256GB DDR5 · 8TB NVMe~₹8L~₹1LSmall HFC · ₹100–500 Cr AUM
Single-node server2× H100 (80GB) or 4× L40S · 512GB · 16TB NVMe~₹40L~₹4LMid HFC · ₹500–3,000 Cr AUM
Cluster8× H100 + secondary node~₹2 Cr~₹15LLarge HFC / NBFC; group-shared infra
Sovereign cloudYotta Shakti / E2E reservedOpex-only~₹80L–₹3 CrLenders without DC capacity
Public cloud (private VPC)AWS / Azure / GCP India regionOpex-only~₹1.2–4 CrExisting public-cloud commitments + DPO sign-off
NEXT

Run your HFC
as code.

Schedule an architecture briefing. We'll walk your head of IT and head of credit through a topology that fits your AUM and your inspection calendar.

The platform