惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

人人都是产品经理
人人都是产品经理
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
宝玉的分享
宝玉的分享
月光博客
月光博客
爱范儿
爱范儿
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
WordPress大学
WordPress大学
有赞技术团队
有赞技术团队
阮一峰的网络日志
阮一峰的网络日志
博客园_首页
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
博客园 - 三生石上(FineUI控件)
博客园 - 聂微东
小众软件
小众软件
量子位
MongoDB | Blog
MongoDB | Blog
Blog — PlanetScale
Blog — PlanetScale
The Cloudflare Blog
Stack Overflow Blog
Stack Overflow Blog
U
Unit 42
Hugging Face - Blog
Hugging Face - Blog
T
The Blog of Author Tim Ferriss
H
Help Net Security
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
git-commit-at: Generate conventional commit messages loca...
bhargavirengarajan21 · 2026-06-16 · via DEV Community

bhargavirengarajan21

We all know the commit history that looks like this:

fix
wip
actually fix
update
FINAL fix
AI tools can help, but most of them send your code diff to the cloud and require a paid API key. That's a non-starter for private repos or sensitive codebases.

What I built
git-commit-at is an npm CLI that analyzes your staged diff and suggests 3 conventional commit messages using a locally-running AI model. Nothing leaves your machine.

npm install -g git-commit-at
Then, in any git repo:

git add .
git-commit-at
You get an interactive prompt to pick a message, optionally add a ticket number (JIRA, Linear, etc.), and confirm. Done.

How it works under the hood

git-commit-at (CLI)

├── Checks if Docker services are running
│ ├── Ollama — runs qwen2.5-coder:1.5b locally (port 11434)
│ ├── Redis — session + cache (port 6379)
│ └── Gradio — web UI for login/history (port 7860)

├── Reads your staged git diff
├── Streams 3 commit suggestions from Ollama
├── You pick one (and optionally add a ticket prefix)
└── Runs git commit
On first run, Docker pulls the model (~1 GB) and starts the services. After that, suggestions take about 5–10 seconds.

Features
Feature Details
AI suggestions 3 per run, based on your actual diff
Conventional commits feat:, fix:, refactor:, chore:, etc.
Ticket integration Prefix with JIRA/Linear ticket numbers
Branch visualizer Live git DAG in the web UI
Commit history Tracked across all your repos
Fully offline After first model download
Privacy 100% local — no data sent anywhere
Requirements
Docker (all backend services run in containers)
Node.js 18+
That's it. No Ollama install, no Python setup, no API keys.

Install

npm install -g git-commit-at
GitHub: https://github.com/bhargavirengarajan21/git-commit-at
npm: https://www.npmjs.com/package/git-commit-at
Hugging face: https://huggingface.co/spaces/build-small-hackathon/git-commit-app

Feedback welcome — especially on the Docker requirement and model choice. I'm considering making the model configurable as a first-class setting.

Both posts are ready to copy-paste. For dev.to, paste as Markdown and set the tags to git, ai, opensource, devtools. Add a cover image and a demo GIF if you have one — posts with visuals get significantly more reach there.