Room · Agents that can be checked

AI & Agents

Agents, MCP tooling and automation, built so that the deterministic parts stay deterministic and every model call has a job it can be judged on.

9 projects · 5 featured

9 projects

01Security tooling · Hackathon

Hemostat

Repair a binary you have no source for — offline — and prove the repair

The Sanjeevani pipeline takes a stripped ELF binary and nothing else: fuzz it to a crash, lift the faulting function back to C, write a fix, splice it into the binary, and prove the bug is gone while behaviour elsewhere is unchanged.

Python
AFL++
Ghidra
Patcherex2
angr

Case studyHackathon prototype

$ ./demo.sh
stack_overflow   unbounded strcpy  (CWE-121)   PROVEN    0x401190
off_by_one       i <= n loop bound (CWE-193)   PROVEN    0x401228
format_string    printf(user_input)(CWE-134)   BOUNDED   —

FIND+READ 13.9s   WRITE 0.1s   SPLICE 3.2s   PROVE 2.9s   TOTAL 20.2s
remote connections: 0 (strace-verified)   disk: 8.6 GB

02Web app · AI video

Reel Studio

Turn class recordings and one-line topics into publish-ready reels

Two pipelines feed one timeline: long recordings become ranked 30–60 s highlights with code-following 9:16 framing and word-synced Hinglish captions; topics become short explainers with a script, code cards and voiceover.

Next.js 16
React 19
FastAPI
Supabase
faster-whisper

Case study Live demo ↗Live demo

Reel Studio landing page on the live deployment

03AI agent · 3rd prize, Hack4Humanity 2026

KisaanRaksha

An early warning for farmer financial distress, in Marathi on WhatsApp

A Financial Stress Index per district from four grounded signals, a Marathi voice agent on WhatsApp whose every fact comes from an MCP tool, and an officer dashboard that raises an alert above a critical threshold.

Python
FastAPI
FastMCP
LightGBM
Whisper

Case study3rd prize · Hack4Humanity 2026

A Marathi WhatsApp conversation showing a simulated critical FSI alert for Amravati

04Developer tool · Security

Agent Fleet

A generated swarm of test agents that red-teams MCP servers

Agent Fleet reads a server's live tool manifest, generates 305 single-purpose worker specs from 12 squad templates, runs them with bounded concurrency, has a judge grade every failure, and files tickets for the real bugs.

Python
FastAPI
asyncio
MCP
Gemini

Case study Live demo ↗Live demo

05Android + engine · SIH 2026

Veris

Fraud checks that cite their evidence, and a ledger that can't be quietly edited

Deterministic checks against named sources produce every verdict, each signal with its citation; a language model only explains the evidence in plain English or a regional language. Incidents go into a tamper-evident ledger and an NCRP-ready packet.

Python
FastAPI
Expo / React Native
Groq

Case studyHackathon prototype

Veris home screen on Android: paste a link, SMS, UPI id or number to check it, with share-sheet, email forensics, QR and screenshot checks

06Agent skill · CLI

OSS-Forge

Issue to verified patch, with a proof-of-fix capsule

Maps the repository, packs only the definitions that matter into a token budget, has Gemma 4 write a regression test and a minimal patch, and marks a fix VERIFIED only when the test fails before and passes after in a fresh worktree.

Python
Gemma 4
git worktrees
Docker sandbox

Case studyPrototype

$ oss-forge solve <repo> --issue <n>
map → context → hypotheses → reproduce → patch → verify
verdict: VERIFIED   (test fails on base, passes with patch, no new suite failures)
capsule: proof-of-fix.json + proof-of-fix.md

07Automation · n8n

REVA

An n8n real-estate agent for property search and lead follow-up

A webhook-driven n8n workflow where AI agents answer property queries, recommend listings by budget and location, estimate affordability, capture leads to Google Sheets and send follow-ups by email.

n8n
Groq
Gemini
Google Sheets
Gmail

Case studyAutomation project

The REVA n8n workflow: webhook, AI agents, Google Sheets and automated replies

08Internship project

FaultLine

Network-fault diagnosis: a rule engine and an AI, judged by a human

A deterministic Python rule engine and an AI model read identical evidence from a Packet Tracer topology; findings are shown side by side and a human accepts, edits or rejects each AI recommendation before the fix is applied and re-tested.

Python
Gemini / Grok
Cisco Packet Tracer
Next.js

Case study Live demo ↗Internship project

FaultLine running the full pipeline: rule engine and AI agreement on injected faults

09AI agents · Edtech

ExamPrepAI

Study material in, quizzes and weak areas out

Agents extract topics from study material and generate JEE-pattern quizzes and flashcards, then track weak areas.

Node.js
Express
Python
Vertex AI Agent Builder

Case studyIn development

AI agents · Edtech

Topic extraction
Quiz & flashcard agents
Weak-area tracking

In development