Klaudia — Plataforma Agentic de Contabilidade Financeira
Laoode/agentic-data-entry
Agentes IA para entrada de dados financeiros com erro zero em produção
Ver no GitHubMCP server para automação de processamento de documentos financeiros, extração de recibos e lançamentos em planilhas. Combina multi-agentes com LangGraph, validação humana e observabilidade completa (Langfuse) para garantir precisão contábil em produção.
Instalação
npx convez-ai Laoode/agentic-data-entry1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Automação de extração de recibos e notas fiscais em PDF
- Lançamento automático de dados financeiros em Google Sheets
- Processamento de documentos multi-página com validação humana
- Orquestração de fluxos contábeis complexos com agentes especializados
Veredito

Solução robusta e production-ready para automação contábil agentic, com arquitetura sofisticada (LangGraph + MCP + Langfuse). Adequado para times que precisam processar documentos financeiros em escala com garantia de qualidade e rastreabilidade completa.
README
A tradução para o português deste README ainda está na fila.
🏵 Overview
Klaudia is an end-to-end agentic finance accountant AI platform designed to automate financial document processing, receipt extraction, data entry operations, and spreadsheet workflows.
Unlike traditional OCR systems, Klaudia combines document intelligence, multi-agent orchestration, human-in-the-loop validation, and production-grade LLMOps into a single architecture.
Core Capabilities
- Receipt & invoice extraction
- Multi-page PDF processing
- Human-in-the-loop correction workflow
- Google Sheets automation
- SQLite financial document registry
- LangGraph multi-agent orchestration
- MCP-based tool execution boundary
- Fine-tuned Qwen 3.5 financial document understanding
- Async document processing pipeline
- Langfuse observability & tracing
- Mobile-first conversational interface
🐸 System Architecture
Agentic Flow
User
│
▼
Guardrails
│
▼
Extraction Agent
│
▼
Supervisor Agent (Klaudia)
│
├── SQL Agent
│ ▼
│ MCP SQLite
│
└── Data Entry Team
▼
MCP Google Sheets
🐝 Training Pipeline
Fine-Tuning Strategy
- Base Model: Qwen 3.5 4B
- PEFT LoRA Fine-Tuning
- Hyperparameter Search
- Experiment Tracking with Weights & Biases
- KIEVal Evaluation Suite
- ANLS*, Digit Accuracy, and JSON Validity Assessment
🍀ྀི Benchmark Results
The Klaudia model (Qwen 3.5 4B fine-tuned on our financial receipt dataset) was evaluated using KIEVal, ANLS*, Digit Accuracy, and JSON Validity benchmarks.
Across all evaluation metrics, Klaudia consistently outperformed the base Qwen 3.5 and Gemma 4 models, demonstrating superior entity extraction, document structure understanding, numerical accuracy, and reduced human correction effort.
Evaluation Summary
| Model | Entity F1 | Group F1 | Aligned | ANLS* | Digit Accuracy | JSON Validity |
|---|---|---|---|---|---|---|
| Gemma 4 E2B-it | 49.29 | 11.04 | 39.72 | 36.22 | 50.83 | 99 |
| Gemma 4 E4B-it | 58.61 | 18.46 | 51.17 | 73.49 | 60.38 | 100 |
| Qwen 3.5 2B | 58.88 | 18.40 | 50.36 | 68.96 | 71.15 | 98 |
| Qwen 3.5 4B | 69.93 | 28.17 | 63.05 | 77.22 | 77.87 | 100 |
| Klaudia (Qwen 3.5 4B Fine-Tuned) | 87.30 | 70.26 | 84.82 | 93.38 | 93.78 | 100 |
Key Improvements Over Base Qwen 3.5 4B
- +17.37% KIEVal Entity F1
- +41.99% KIEVal Group F1
- +21.77% KIEVal Aligned
- +16.16% ANLS*
- +15.91% Digit Accuracy
- Maintained 100% JSON Validity
🎞️ Dataset & Models
[!WARNING] The dataset and fine-tuned model will be released after the research paper is published. They are currently archived in a private Oxen.ai repository.
Dataset Sources
- Hugging Face
- Kaggle
- Roboflow
- X (Twitter)
- Custom Collected Receipts
- Human Verified Labels
🏞️ Mobile Application
Mobile Stack
- React Native
- Expo
- TypeScript
- Session Management
- Conversational Finance Assistant
- Receipt Upload Workflow
- Spreadsheet Operations
🍏 Tech Stack
| Layer | Technologies |
|---|---|
| Backend | FastAPI |
| Agent Framework | LangGraph |
| LLM Framework | LangChain |
| Models | Gemini 3.5, Qwen 3.5 |
| Fine-Tuning | LoRA, PEFT |
| Inference | vLLM |
| Queue | Redis, Taskiq |
| Storage | SQLite, MinIO |
| Hashing | BLAKE3 |
| Tool Layer | MCP |
| Spreadsheet Integration | Google Sheets |
| Observability | Langfuse |
| Containerization | Docker, OrbStack |
| Frontend | React Native, Expo |
| Experiment Tracking | Weights & Biases |
🪲 Key Features
Financial Document Intelligence
- Receipt Extraction
- Invoice Extraction
- OCR + KIE Pipeline
- Multi-page PDF Support
- Structured JSON Generation
Agentic AI System
- Supervisor Architecture
- Multi-Agent Collaboration
- MCP Tool Execution
- Human-in-the-Loop Workflow
- Session-Aware Context Management
Production Infrastructure
- Async Processing
- Queue-Based Execution
- Observability & Tracing
- Object Storage
- Deduplication Pipeline
- Fault-Tolerant Processing
🗂️ Repository Structure
app/
├── routes/
├── services/
├── extraction/
├── guardrails/
└── core/
klaudia/
├── supervisor/
├── sql_agent/
├── data_entry_team/
└── tools/
mcp-sqlite/
mcp-gsheets/
docs/
tests/
sample-data/
🍀 Mission
Where financial records lose balance, Klaudia restores order.
Klaudia is designed around a simple philosophy:
Inputting financial data is not merely typing numbers. It is preserving the financial truth of an organization.
📗 Research
This project is part of an undergraduate research thesis focused on:
- Agentic AI Systems
- Financial Document Intelligence
- LLMOps Pipelines
- Human-in-the-Loop Data Entry Automation
- Domain Adaptation for Financial OCR
Dataset and model release will follow publication.
🔰 Author
Yudhy Prayitno
Building agentic systems for real-world financial automation.