Formea AI Form Automation
Multi-Agent Chrome Extension for Intelligent Form Filling
Solo-built full-stack AI Chrome Extension: Plasmo MV3 frontend with React, Express.js + MongoDB backend, and LangChain multi-agent AI layer. 8 LLM providers, VBON Form Explorer for government portals, template system with dependency management, and Clerk Auth across all layers.
Key Features
- Solo-built full-stack: Plasmo Chrome Extension + Express.js API + LangChain agent layer
- Multi-agent system with 3 specialized agents and self-validation loops
- 8 LLM providers with automatic structured output fallback
- VBON Form Explorer for government form reverse-engineering
- MongoDB persistence for templates, profiles, and form dependency graphs
- Clerk Auth across Chrome Extension and backend API
Tech Stack
AI & Agents
Backend
Frontend
LLM Providers
Challenges & Solutions
Complex Government Forms (VBON)
Government forms (PrimeFaces/JSF) have 10K+ lines of HTML with repeated IDs, inline JavaScript handlers, and dynamic AJAX updates — traditional scraping approaches fail entirely.
Built VBON Form Explorer agent using stable hash-based IDs (XPath + role + label) that survive DOM changes, PrimeFaces AJAX completion detection, and deterministic DOM diffing to build field dependency graphs.
Agent Coordination & State Management
Three agents need shared browser context, real-time UI updates from background worker, and graceful error handling across agent boundaries.
Shared AgentContext with BrowserContext, EventManager for real-time UI updates, and generic BaseAgent<T extends ZodType> enforcing type-safe structured outputs per agent.
Models Without Structured Output Support
Not all LLM providers (DeepSeek Reasoner, Llama) support native JSON schema output — agents need consistent Zod-validated responses regardless of provider.
Automatic fallback pattern: detect provider capability, use native withStructuredOutput() when available, fall back to manual JSON extraction + Zod validation for unsupported models. Provider-agnostic agent code.