VOBC

VOBC / oh-my-coder

Public

🤖 Multi-Agent AI Coding Assistant - 支持DeepSeek/文心/通义，节省30-50% Token成本

github.comVOBCoh-my-coder agent ai automation coding deepseek
19
4
89% credibility
Found Apr 13, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Oh My Coder is an open-source multi-agent AI coding assistant supporting Chinese large language models for tasks like code generation, review, debugging, and testing via CLI and web interfaces.

How It Works

1
🔍 Discover Oh My Coder

You find this free AI coding helper on GitHub, perfect for building apps without expensive subscriptions.

2
📥 Easy Setup

Run a simple script to install everything on your computer in minutes.

3
🔗 Connect Your AI Helper

Add a free AI service connection so the smart agents can understand and create code.

4
💬 Describe Your Project

Tell it what you want to build, like a simple to-do list app, in everyday words.

5
🤖 Watch Agents Collaborate

See the team of smart helpers explore, plan, write, and test your code step by step.

6
✅ Review and Tweak

Check the generated code, make any small changes, and run it to see it work.

🎉 Your App is Ready!

Enjoy your fully working project, ready to use or share with friends.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is oh-my-coder?

Oh-my-coder is a Python-based multi-agent coding AI that orchestrates 30 specialized agents to handle full dev workflows like building APIs, code reviews, debugging, and testing. Developers run tasks via CLI (`omc run "add user CRUD"`), web dashboard at localhost:8000 with real-time SSE progress, or VSCode extension, all powered by free Chinese LLMs like DeepSeek and GLM to cut token costs 30-50%. It scans your workspace, plans steps, generates/runs/tests code, and supports async "Quest" mode for background execution with notifications.

Why is it gaining traction?

Unlike Claude multi-agent GitHub tools or GitHub Copilot multi-agent systems requiring VPNs and $20/month subs, this delivers a github multi agent framework with zero-cost domestic models, Chinese-first prompts, and local/self-hosted runs. Multi-agent coding workflows shine in build/review/debug pipelines, with smart routing picking cheap/fast models automatically—devs notice faster iterations without token burn. Docker/VSCode setup makes it a drop-in multi agent coding tool for any IDE.

Who should use this?

Backend devs prototyping REST APIs or fixing bugs in FastAPI/Django projects; full-stack teams automating code reviews/security scans; Chinese developers building multi agent coding setups without Copilot bills or foreign LLM access. Ideal for solo coders handling tedious tasks like test generation or git ops in resource-constrained environments.

Verdict

Promising multi agent coding system for cost-conscious teams, but early maturity shows in 19 stars and 0.9% credibility score—docs are solid, tests cover basics, yet expect rough edges. Try via `pip install -e .` if token savings matter; skip for production until stars climb.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.