Apache-2.0 · Offline-first · Multilingual · Built on the public education commons

Give India's 1 crore teachers their hours back.

Learn Clue is an open-source AI toolkit that automates the highest-friction classroom workflows — grading handwritten answers, setting question papers, generating mother-tongue notes — designed to run on every tier of Indian school infrastructure, from no-electricity rural schools to fully-connected urban ones, at a cost of single-digit rupees per task.

Runs on efficient, low-cost AI — fast and affordable from one classroom to a whole state.

14.71 L
schools
UDISE+ 2024-25
24.8 Cr
students enrolled
1.01 Cr
teachers
36.5%
schools with no internet

The central design constraint

One country, three completely different schools.

A national tool that assumes connectivity excludes the schools that need help most. Here's the real infrastructure picture from UDISE+ 2024-25 — the gap between "has electricity" and "has working internet" is the whole problem.

Source: UDISE+ 2024-25, Ministry of Education, Govt. of India. Functional %, national average.

Tiered degradation, not feature gating

The same workflow runs everywhere — it just degrades gracefully.

Premium schools don't get features poor schools are denied. Every tier gets the workflow; the model quality and latency adapt to what the school has.

T0

No power · No internet

Paper + a phone that's briefly charged. Capture now, queue, sync and process later. Fully on-device / edge open models — zero recurring API cost.

  • Photograph scripts when a device is free
  • Batch-grade overnight, print & return
  • On-device OCR + small open LLM
T1

Shared devices · Intermittent net

The majority of Indian schools. A single mini-PC at a Block Resource Centre serves a cluster. Open models do the bulk; a frontier model is reserved for hard judgment.

  • Edge node syncs when online
  • Open-model transcription + selective escalation
  • Per-school budget caps
T2

Connected · 1:1 or lab

Funded / private schools. Full cloud routing — the value (teacher-hours returned) dwarfs the cost. Frontier vision + reasoning on every task.

  • Real-time grading & feedback
  • Misconception analytics for the class
  • DIKSHA / WhatsApp integrations

See it in action

How AI does the heavy lifting.

Animated walkthroughs of the core workflows — from a phone photo of a handwritten script to a graded result, from a textbook to a ready exam paper, and a camera that watches an exam hall so a teacher doesn't have to.

Handwritten answer script AI reads it (HTR) script-id: 0427 · lang: Devanagari confidence: 0.93 vs marking scheme reactivity oxidation exothermic 8/10 graded draft
Snap a photo on any phone Instant graded feedback 4/5 confidence 91% ✓ method correct ✓ units shown ✗ final step missed मातृभाषा में फ़ीडबैक अच्छा प्रयास! अगली बार अंतिम चरण ज़रूर लिखें।
Textbook (online or scanned) Chapter 1 Blueprint constraints MCQ Short Long Σ = 20 marks · Bloom-spread Ready paper + key QUESTION PAPER 20 marks ✓
Live camera · exam hall ● REC ! AI proctor 24 present 22 on-task ⚠ seat C3 looking at neighbour Privacy: faces tokenised on-device · no cloud upload teacher confirms every flag
Photo of paper register # Name P/A 1 2 3 4 5 Structured digital roster Aarav S. Diya P. Kabir M. Meera J. Present 38 / 40
After-hours doubt — grounded strictly in the textbook Why is the sky blue, didi? — student, Class 7 thinking… AI tutor Sunlight scatters off tiny air particles. Blue light scatters most — so the sky looks blue. (Class 7 Science, Ch. 11) 📗 Grounded source no open-web guessing
A1 Photograph a stack of scripts, AI transcribes the handwriting, grades each answer against the marking scheme, and flags low-confidence ones for the teacher.

Live prototype — really runs

Try the two MVP workflows.

Real AI, live. Switch the engine below and watch the same task run on the fast-and-free path or the scale path — each result shows the speed and the per-task cost in rupees. Teacher-in-the-loop: every output is a reviewable draft, never a final mark.

AI engine:
Results appear here →
A blueprint-compliant paper appears here →
A simplified, mother-tongue explainer appears here →

⚠️ Shared public demo — rate-limited and capped. Outputs are AI-generated drafts for demonstration; in a real deployment a teacher reviews and overrides every result.

Computer vision · live on your device

Scan handwriting. Watch the exam hall.

Real AI on an image from your camera or a file — handwriting OCR that reads a scanned script and grades it, and a camera-feed exam proctor. Fast, low-cost, and built to scale across a whole district.

📄

Upload or snap a photo of a handwritten answer

On a phone this opens the camera. JPEG/PNG, downscaled in-browser.
Transcription + grade appear here →
Camera off

Frames are analysed for integrity signals and discarded — nothing is stored. The AI assists a human invigilator; it never accuses.

Integrity log appears here →

🔒 Your camera frames are sent to the model only while you actively use the tool, then discarded. Grant camera permission when prompted.

§7 of the spec — the most important cost decision

Route by judgment required, not by default to the biggest model.

Most classroom tasks are cheap extraction. A minority need reasoning. A small fraction need deep reasoning. Honest routing — a 70/20/10 split — cuts cost by more than half with negligible quality loss.

Prompt cachingup to −90% on the rubric/blueprint reused across a whole class set
Batch processing−50% — grading & overnight paper-gen aren't latency-sensitive
Open-model floorevery step has an open-weights fallback — the toolkit never hard-locks to one vendor

A toolkit, not a single app

The workflow catalogue.

Each module is chosen because it returns hours to a teacher — not because it's technically interesting. The two highlighted are the live MVP.

Scale

Built to grade a whole state by morning.

When exams end, a district becomes a mountain of scripts. Learn Clue grades each one in seconds for a few rupees — and it runs the same whether one classroom or an entire state board uploads at once. So feedback arrives in days, not weeks, teachers get their evenings back, and a public system can actually afford it. The whole education system, at AI speed.

⚡ ~6s per script · ₹~3 per script — flat at every scale Classroom 40 students School ~1,200 District ~90,000 State board ~1.2 crore
~6s
to grade one script. A district's whole exam — overnight, not over a month.
₹~3
per script. Cheap-LLM intervention keeps it affordable from one school to a state.
results day
built to absorb the exam-week surge, so it's there exactly when it matters most.
online · off
runs on a connected lab or a rural school's single shared phone — same workflow.

Business model

Priced per school, not per seat.

Open-core: the toolkit is free and self-hostable forever. Revenue comes from managed hosting, the enterprise scale plane, and district-level integrations & support.

Community

₹0/forever

Self-host the open-source toolkit.

  • ✓ Grading, paper-gen, OCR, explainers
  • ✓ Runs on free / local AI models
  • ✓ Apache-2.0 — yours to run
  • ✓ Community support
Get the code
Most schools

School Pro

₹4,999/school/mo

Managed, zero-ops, up to ~40 teachers.

  • ✓ Hosted & auto-updated
  • ✓ Enterprise Azure scale plane
  • ✓ Live camera proctoring
  • ✓ DPDP consent ledger & redaction
  • ✓ Email support, 99.9% SLA
Start a pilot

District / Board

Custom

State boards, exam councils, school chains.

  • ✓ Dedicated multi-region capacity
  • ✓ UDISE+/APAAR & DIKSHA integration
  • ✓ On-prem / edge for T0/T1 schools
  • ✓ Custom rubrics & board patterns
  • ✓ Onboarding & training
Talk to us

Pricing illustrative for the investor prototype. Unit economics: see README §8 — single-digit-rupee cost per graded script keeps gross margin high even at the School Pro price.

Built in the open

A genuine public good — Apache-2.0, built on the commons.

Learn Clue extends India's public education infrastructure — DIKSHA / Sunbird, Bhashini, openly-licensed NCERT content — instead of rebuilding it. The toolkit must run with no paid API at all (open models are the floor); frontier models like Claude are the quality ceiling it routes to when a school can fund it.

  • ✅ Permissive Apache-2.0 license — maximizes adoption & dependency
  • ✅ Vendor-neutral — never locked to one AI provider
  • ✅ DPDP-Act-aligned privacy: on-device redaction, consent ledger, teacher-in-the-loop
  • ✅ Offline-first so it reaches the schools that need it most

The path to credibility

Ship publicly → deploy to 5–10 real schools → measure teacher-hours saved & grading accuracy → apply via the discretionary "ecosystem depends on it" path with evidence.

P0 Grading engine + router
P1 Question-paper generation ← MVP live now
P2 Redaction + offline edge deploy
P3 Multi-board + analytics
P4 DIKSHA / UDISE / WhatsApp