AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

Chintannn-c/AI-Audit

StatAudit AI Platform: An autonomous auditing infrastructure with a hardened 8-tier AI failover system (Gemini 3.1/2.0, Hugging Face Qwen2-VL, and Offline OCR) for hyper-accurate invoice vouching and risk assessment.

Python GitHub ↗
★ 0
stars
65
AI relevance
50
solo dev
0
tool sigs

SUMMARY AI summary by gpt-5-mini

StatAudit AI is an enterprise auditing platform that automates invoice vouching, risk assessment, and smart audit sampling for audit teams, internal/external auditors, and finance/compliance groups. Key features: - Multi-tier AI orchestration with direct Mistral Large integration and OpenRouter auto-routing/failover; model routes defined for forensic reasoning, fast scanning, and OCR/vouching. - Live telemetry dashboard showing model latency, health and quotas. - Hardened sampling engine that guarantees exact sample sizes, enforces phased unique-vendor selection and a strict vendor repetition cap (max 2 appearances). - Materiality and quantitative/qualitative risk engines, plus automated 5-sheet Excel working papers with flexible field mapping. - Tech stack: FastAPI, MongoDB, HTTPX, React; secrets kept in backend/.env (gitignored).

DETECTED Detected AI stack

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.

🧠 LLM providers (3)
Hugging Face Mistral Gemini
🤖 LLM models (3)
Mistral Gemini Qwen
💾 Databases (1)
MongoDB
🌐 Web frameworks (2)
FastAPI React

Language breakdown (by bytes)

CSS
10.7%
HTML
19.4%
Python
51.2%
Procfile
0%
JavaScript
18.7%

Owner

Account
Chintannn-c
Type
User
Followers
1

Dates

Created on GitHub 2026-05-11
Last push 2026-05-11
First seen here 2026-05-11
Last fetched 2026-05-11 16:10

Similar repos (same language)

bgzhang1/sw2api

Reverse proxy for your ai quota from the SW platform.

Python 19 AI 45
dea6cat/2b-agent

This llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus

Python 1 AI 75
Zuboy/Carbon-Cost-Optimizer-Agentic-AI

An AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.

Python 1 AI 75
FuchaZ/lm-studio-vision-bridge

给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务

Python 1 AI 45
Shrutirowlo/AI-Video-Agent

AI-powered video generation agent that automates script analysis, scene planning, and video creation.

Python 1 AI 75
Shivang0/social-vision

Paste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.

Python 1 AI 70
markusbegerow/claude-fuer-oeffentliche-verwaltung

⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.

Python 1 AI 75
knowledgegut/course-distiller

把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF;最後的重組交還人腦。A Claude Code skill by 知識包小腸.

Python 1 AI 45