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.
UDISE+ 2024-25
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.
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
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
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.
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.
⚠️ 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.
Frames are analysed for integrity signals and discarded — nothing is stored. The AI assists a human invigilator; it never accuses.
🔒 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.
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.
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
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
School Pro
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
District / Board
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
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.