Satbara Saathi: Understand Your 7/12 Land Record in Marathi, Without the Talathi Trip

A developer built Satbara Saathi, an open-source tool that explains Maharashtra 7/12 (Satbara) land extracts in plain Marathi, Hindi or English by combining OCR, 11 deterministic red-flag rules and an LLM explanation layer. The rules engine contains no AI, and the LLM is restricted to explaining flags it is handed and barred from calling land "safe" or "valid". Built in one week under Apache-2.0, the project currently runs on fake providers, with structured extraction from real OCR output unfinished and the rules not yet reviewed by a revenue-law professional.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady https://dev.to/challenges/hacktoberfest-week3-2026-10-19 What I Built Satbara Saathi सातबारा साथी explains a Maharashtra 7/12 Satbara land extract in plain Marathi, Hindi or English. A 7/12 is dense, jargon-heavy and often scanned badly. Anyone buying or inheriting farmland ends up waiting at the talathi office or paying a middleman to read it to them. The lazy way is to upload a photo and get the answer back: 1. Preprocess the image and check its quality 2. OCR it and extract structured fields 3. Run 11 deterministic red-flag rules loan/boja, multiple owners, minor owner, tenant, Class 2 land, inheritance mutation, area mismatch, and more 4. Have an LLM explain the findings in simple language 5. Read the summary aloud TTS The most important design decision is what the AI does not do. The rules engine contains no AI. The LLM only explains flags it is handed, and it is told never to call land "safe" or "valid". The tool gives no legal advice and says so. Demo Code Satbara Saathi सातबारा साथी Understand Maharashtra 7/12 Satbara extracts in plain Marathi / Hindi / English . What it does 1. Reads a 7/12 image scanned or digital 2. Extracts structured data via OCR 3. Runs deterministic red-flag rules no AI in the rules engine 4. Explains findings in plain language via LLM 5. Speaks the summary aloud TTS What it does NOT do - Give legal advice - Decide if land is "safe" - Store your images or personal data - Process 8A, mutation extracts, or other states yet Quick start Architecture Privacy - Images deleted after processing - No PII in logs - Anonymous impact counters only - Consent gate before upload License Apache-2.0 How I Built It - Backend: FastAPI + Pydantic. Providers sit behind small interfaces OCR, LLM, TTS , so each can be swapped by config. - Rules: app/rules/mh 7 12.yaml , with bilingual Marathi/English titles, explanations and "what to do next" steps per rule. They are plain data, so a revenue-law professional can review them without reading Python. - LLM: the explain layer targets Sarvam-M , an open-weight 24B model post-trained on Mistral Small 3.1 with Marathi and Hindi support. A post-check rejects explanations containing names or long numbers that aren't in the source document, and retries once before failing. - Privacy: consent gate before upload, jobs held in memory only, and the only thing persisted is an anonymous counter DB no names, no survey numbers, no images . - Tests: 16 tests pass using fake providers, with CI on GitHub Actions. Honest status: this is a one-week build. The Sarvam and OCR adapters are written, but the running server currently uses fake providers, and structured extraction from real OCR output is not finished. The rules engine, validation, explanation safeguards, consent flow and UI work end to end on sample data. The rules have not yet been reviewed by a Maharashtra revenue-law professional, which is the first thing needed before any real use. Why Does Open Innovation Matter? A land record contains names, family relationships and where someone's livelihood sits. That is exactly the data you don't want flowing through a black box. - Self-hostable explanations. Because Sarvam-M has open weights, a gram panchayat, CSC centre or NGO could run the explain step on its own server with vllm serve and keep documents off third-party systems. A closed API would not allow that. - Auditable rules. The red-flag logic is open YAML, not model behaviour, so lawyers and community members can read, challenge and correct it. - Built for the language. A model post-trained on Indic languages is what makes Marathi output realistic. Apache-2.0 means anyone can adapt this for other states. The OCR and TTS adapters currently call hosted APIs. Replacing them with open models is the clearest next step.