convez.ai
MCP ServerFinanceiroAvançado
Laoode

Klaudia — Plataforma Agentic de Contabilidade Financeira

Laoode/agentic-data-entry

Agentes IA para entrada de dados financeiros com erro zero em produção

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP 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-entry

1 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

Estrelas
9
Forks
4
Acompanhando
0
Saúde
28%
Último commit
há 1 dia
Versão
—
Issues abertas
13
Contribuidores
2

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

ModelEntity F1Group F1AlignedANLS*Digit AccuracyJSON Validity
Gemma 4 E2B-it49.2911.0439.7236.2250.8399
Gemma 4 E4B-it58.6118.4651.1773.4960.38100
Qwen 3.5 2B58.8818.4050.3668.9671.1598
Qwen 3.5 4B69.9328.1763.0577.2277.87100
Klaudia (Qwen 3.5 4B Fine-Tuned)87.3070.2684.8293.3893.78100

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
  • Pinterest
  • 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

LayerTechnologies
BackendFastAPI
Agent FrameworkLangGraph
LLM FrameworkLangChain
ModelsGemini 3.5, Qwen 3.5
Fine-TuningLoRA, PEFT
InferencevLLM
QueueRedis, Taskiq
StorageSQLite, MinIO
HashingBLAKE3
Tool LayerMCP
Spreadsheet IntegrationGoogle Sheets
ObservabilityLangfuse
ContainerizationDocker, OrbStack
FrontendReact Native, Expo
Experiment TrackingWeights & 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.

Ver o original no GitHub

Bom para

Relacionados