Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
AI Bank Statement Document Automation By LLM model and Personal Finanical Analysis
| Date | Stars |
|---|---|
| 2026-07-31 | 601 |
| 2026-08-05 | 616 |
| 2026-08-06 | 616 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# AI Bank Statement Automation with LLM & Personal Financial Analysis [](https://www.python.org) [](https://github.com/crewAIInc/crewAI) [](https://docs.langchain.com/oss/python/deepagents/overview) [](https://hermes-agent.nousresearch.com/) [](https://github.com/BerriAI/litellm) [](https://opensource.org/licenses/Apache-2.0) > **Intelligent document automation for bank statements** — Extract, structure, analyze, and query financial data from PDFs using **YOLO + OCR + LLM**, with **parallel agent harnesses** (CrewAI, Deep Agents, Hermes) and **local LLMs** (LM Studio / Ollama). --- ## Key Features - **Advanced PDF Parsing** — YOLO layout detection + OCR + LLM-based table extraction - **Multi-harness agents** — CrewAI baseline, LangChain **Deep Agents** (agentskills.io), **Hermes** (Docker sandbox) - **Agent Skills** — Domain skills for bank-statement parsing, PII redaction, financial analysis, RAG, and output format - **Local LLM First** — LM Studio and Ollama via LiteLLM (async `acompletion`) - **Reasoning Model Support** — Handles models that return content in `reasoning_content` - **Secure RAG Pipeline** — PII redaction **before** embedding into vector database (Qdrant / Chroma) - **Financial Intelligence** — Income/expense categorization, trend analysis, natural language querying - **Full-Stack API** — FastAPI + PostgreSQL + Celery + React SPA (REST auth, async document processing, agent runs) - **GPU Acceleration** — NVIDIA GPU support for PyTorch embeddings and LLM inference (<2× build time vs CPU) - **Development Notebook** — Jupyter notebook for CrewAI experimentation - **MLflow Integration** — Trace LLM calls and agent workflows (CrewAI path) --- ## Important Notes for Local LLMs (LM Studio / Ollama) When using **local models** via LM Studio or Ollama: - **Model size**: Prefer **9B+** parameters (e.g. Qwen2.5-14B, Qwen3-27B, Gemma-2-9B, Llama-3.1-8B+). Smaller models reduce quality. - **Context length**: **16K+** tokens (recommended **32K+**). Low context drops agent instructions. - **JSON output**: Local models often fail strict JSON. Prefer **Markdown** reports; post-process with a second call or `instructor` if needed. --- ## Tech Stack | Component | Technology | |-----------|------------| | **API** | FastAPI, SQLAlchemy 2.0 (async), Alembic, Pydantic v2 | | **LLM Orchestration** | LiteLLM (LM Studio, Ollama, OpenAI, DeepSeek, etc.) | | **Agent Frameworks** | CrewAI + Skills · Deep Agents (LangGraph) · Hermes (Docker sandbox) | | **Document Processing** | PyMuPDF, YOLO, OCR | | **Vector Database** | Qdrant, Chroma | | **RAG** | LangChain + PII redaction | | **Async Tasks** | Celery + Redis | | **Database** | PostgreSQL 16 | | **GPU (optional)** | NVIDIA Container Toolkit, PyTorch 2.11+cu128 | | **Frontend** | React 18, TypeScript 5, Vite 5, TailwindCSS 3 (SPA on :80) | | **Tracing** | MLflow (CrewAI path) | --- ## Project Structure ```text AI-Bank-Statement-Document-Automation/ ├── agents/ # Multi-harness agents (experimental) │ ├── README.md │ ├── crewai/ # Skills snapshot + pointer to baseline │ ├── deep-agents/ # deepagents SDK, tools, tests, E2E │ │ ├── run_e2e.py │ │ ├── agent.py │ │ ├── tools/ │ │ ├── skills/ │ │ └── tests/ │ └── hermes/ # Docker-sandboxed Hermes profile │ ├── config.yaml │ ├── scripts/ │ └── skills/ ├── api/
Excerpt of 14,057 characters
Read on GitHub
81
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b15acb5eeb4614cc, topic:ai-agents, topic:crewai
matched fp:b15acb5eeb4614cc, topic:ocr
matched fp:b15acb5eeb4614cc, topic:llm
matched fp:b15acb5eeb4614cc, topic:rag