Quorum — Deep-Research Agent Swarm with a Shared GraphRAG Brain

Problem

Most AI research tools are one model in a loop. It cannot hold a multi-hop question together, it has no second opinion, and vanilla vector RAG fumbles exactly the questions that need relationships rather than similar-looking paragraphs.

Business Impact

Research questions that matter are multi-hop, and a single-model loop answers them confidently and wrongly. A swarm with an explicit Critic and a shared graph makes the reasoning inspectable — you can see which entity connected to which, and which agent found it.

System Approach

• Orchestrator emits events; Planner, N Researchers, Critic, and Synthesizer run against a shared graph
• GraphRAG store on NetworkX plus embeddings, with merge-on-write entity normalization
• Graph-aware retrieval: top-k nodes, neighbour expansion, subgraph to the Synthesizer
• FastAPI backend streams every agent action over SSE
• React and Vite frontend renders the live force graph and the agent roster
• Deterministic demo mode runs with zero config and no keys

Key Decisions & Trade-offs

• Shared graph over message passing — the graph is the coordination substrate, not a side effect
• Merge-on-write so duplicate discoveries converge instead of forking the answer
• An explicit Critic agent, because a swarm without one just agrees with itself faster
• Stream everything as events so the UI is a view of the run, not a summary of it
• Deterministic demo mode so the project can be tried and filmed without an API key

Current Status

Public and open source at github.com/rohitguta2432/quorum. Full swarm, GraphRAG store, and live streaming UI working; runs zero-config in deterministic demo mode and against Anthropic or local Ollama for real research. Design notes in docs/DESIGN.md.

Roadmap

• Persist graphs across sessions so research compounds
• Source-level provenance on every edge
• Configurable swarm shape — researcher count and critic strictness per question

What I'd Improve Next

• Better embeddings by default rather than as an optional install
• Export the built graph to standard formats for downstream tools

Explore More

• MyFinancial — Personal Financial Advisor — Financial planning in India is fragmented across banks, insurance, and tax documents.
• PropCheck — AI Property Trust Score for India — Indian property buyers lose lakhs to fraudulent listings on Magicbricks, 99acres, Housing.
• StellarMIND — Chat-to-SQL with RAG — Business users need to query databases without knowing SQL.
• ClinicAI — WhatsApp AI Clinic Assistant — India has 12 lakh+ small clinics running on phone calls and paper diaries.
• MicroItinerary — AI Travel Planner — Travel apps optimize for proximity and ratings.
• SanatanApp — Hindu Devotional App — Devotional users in India juggle 5+ separate apps for Chalisa, Gita, Aarti, Ramayan, and Mahabharat.
• SynFlow — Enterprise Intelligence Platform — Private deal networks rely on manual introductions and spreadsheets.
• FinBaby (Jama) — Personal Finance Tracker — Indian middle-class families track expenses across UPI apps, bank statements, and paper notebooks.
• RetailOS — Multi-Tenant Retail SaaS — Indian kirana stores and small retailers use paper registers or basic billing software with no inventory tracking, no GST compliance, and no offline support.
• TripHive — Offline-First Collaborative Trip Planner — Group trip planning is fragmented across WhatsApp, Google Docs, Maps, Splitwise, and email.
• ScamRakshak — On-Device AI Scam Detector — Indians lose thousands of crores annually to digital scams via WhatsApp, SMS, and social media.
• PaisaGuard — Family Budget Survival App — Middle-class families worldwide track expenses inconsistently — UPI apps show transactions but don't enforce budgets.
• rohitraj.tech — Engineering work is often invisible.
• Agent Autopsy — Forensic Debugger for Failed AI Agent Runs — Most AI agent failures are silent — the run completes, the status code is green, and the result is still wrong.
• tinyvoice — Fine-Tune a Model in Your Own Voice in an Afternoon — Training your own language model sounds like a PhD job that needs a GPU cluster, so most developers never try.
• snap3d — One Photo In, an Editable 3D Model Out — A photo shows you one side of an object; the other five sides are a guess.
• Agentic OS — Force-Directed Map of a 387-Skill Claude Code Setup — An agent setup grows one plugin at a time until it has hundreds of skills, and nobody can see what it actually contains.
• claude-autodev — Autonomous 8-Stage Dev Pipeline for Claude Code — Agentic coding tools stop at a diff.
• KisanSathi — Six AI Farm Experts, Keyless and Local — Farmer-facing AI tools die at the API-key step, answer in English, and hand back generic advice with no live numbers behind it.
• MarginChef — AI Agent That Finds a Restaurant's Margin Leaks — Restaurants run on 3-5% net margins while food costs are up roughly 35% since 2019, and most owners never see per-dish economics.
• RegexForge — Plain English to a Regex You Can Trust — Regex is not hard because the syntax is exotic.
• Skillet — Turn Any Docs Page Into an Installable Claude Code Skill — Agent skills are the fastest way to teach a coding agent a new tool, but writing a good SKILL.
• Ladle — Open-Source Prep Forecasting and Food-Cost Leak Detection — Restaurants throw away 4-10% of the food they buy before it reaches a plate, and most owners find out at month end from a food-cost percentage that moved the wrong way, with no idea which ingredient did it.
• Casita — Design Your Home in 3D in the Browser — Home design tools want an install, a login, or a CAD background.
• VoxelForge — A Voxel Sandbox Engine Built Properly — Voxel sandboxes are the demo everyone builds with a coding agent right now, and almost all of them are a throwaway single HTML file that hitches on chunk generation, ships a texture pack, and cannot be read or extended.
• prompt-ocean — Type a Sea, Watch It Exist — Generative interfaces usually hand a model the wheel and hope.
• HEXAPOD — Inverse Kinematics and Gait Simulator — Hexapod gait and leg IK are usually explained with equations and a video, or hidden inside a robotics library.
• avatar-sync — Real-Time Face and Hand Tracking in One HTML File — Face and hand tracking demos come wrapped in a build step, a server, and usually an API key — which puts a wall in front of anyone who just wants to see what the models actually output before building on them.
• Reliability & Production Readiness — Load testing, observability, and API contracts.
• Open Source Repos — Browse the source code behind these projects.