DEV Community

niuniu profile picture

niuniu

Full-stack developer & AI enthusiast. Building cool stuff with Python, exploring LLMs, and sharing open-source tools. Currently obsessed with AI coding assistants. Always learning, always shipping.

Location Shanghai, China Joined Joined on  Personal website https://monkeycode-ai.net/ github website
Postmortem: When Agent Retries Hit the Paid Endpoint

Postmortem: When Agent Retries Hit the Paid Endpoint

Comments
8 min read

Want to connect with niuniu?

Create an account to connect with niuniu. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
Postmortem: The Agent That Patched the Wrong Environment

Postmortem: The Agent That Patched the Wrong Environment

Comments
7 min read
Postmortem: The Agent That Shipped a Fix Nobody Asked For

Postmortem: The Agent That Shipped a Fix Nobody Asked For

Comments
7 min read
The Agent Deleted the Assertion: A Monday Postmortem

The Agent Deleted the Assertion: A Monday Postmortem

Comments
8 min read
Auto-Generate CHANGELOG.md with a Free Python AI Webhook

Auto-Generate CHANGELOG.md with a Free Python AI Webhook

Comments
6 min read
Postmortem of a Rogue Chatbot: When Context Becomes the Attacker

Postmortem of a Rogue Chatbot: When Context Becomes the Attacker

Comments
4 min read
A Postmortem of a Silent Timeout: Lessons from Running an LLM Gateway on a Free Server

A Postmortem of a Silent Timeout: Lessons from Running an LLM Gateway on a Free Server

Comments
4 min read
Postmortem: The Prompt Template That Silently Upgraded Every Request

Postmortem: The Prompt Template That Silently Upgraded Every Request

Comments
5 min read
A Routing Postmortem: When the Cheap Lane Stops Being Cheap

A Routing Postmortem: When the Cheap Lane Stops Being Cheap

Comments
4 min read
Postmortem: The 2 A.M. LLM Retry Loop That Paid for Your Silence

Postmortem: The 2 A.M. LLM Retry Loop That Paid for Your Silence

Comments
5 min read
Postmortem: The AI Reviewer Approved a Breaking Change at 2 AM

Postmortem: The AI Reviewer Approved a Breaking Change at 2 AM

Comments
4 min read
Postmortem: The Silent Patch That Broke the Merge

Postmortem: The Silent Patch That Broke the Merge

Comments
4 min read
When the AI Agent Blamed the Database: A Debugging Retrospective

When the AI Agent Blamed the Database: A Debugging Retrospective

Comments
4 min read
My Agent Forgot Everything Mid-Task: A Debugging Retrospective

My Agent Forgot Everything Mid-Task: A Debugging Retrospective

Comments
4 min read
The Agent That Forgot Everything: A Debugging Postmortem

The Agent That Forgot Everything: A Debugging Postmortem

Comments
4 min read
I Deployed 5 Side Projects for $0/Month Using Vercel, Neon, and Cloudflare — Here's the Exact Stack

I Deployed 5 Side Projects for $0/Month Using Vercel, Neon, and Cloudflare — Here's the Exact Stack

Comments
2 min read
Quick Tip: Run Llama 3.1 8B on Colab's Free T4 GPU in 5 Lines of Python

Quick Tip: Run Llama 3.1 8B on Colab's Free T4 GPU in 5 Lines of Python

Comments
1 min read
Quick Tip: functools.cache Made My Recursive Python 30x Faster (One Line)

Quick Tip: functools.cache Made My Recursive Python 30x Faster (One Line)

Comments
1 min read
The Free AI Tier Trap: When "Free" Costs You More Than You Think

The Free AI Tier Trap: When "Free" Costs You More Than You Think

Comments
4 min read
I Ran My Entire Side Project on Cloudflare Workers Free Tier for 6 Months — Vercel Would Have Charged Me $240

I Ran My Entire Side Project on Cloudflare Workers Free Tier for 6 Months — Vercel Would Have Charged Me $240

Comments
3 min read
Quick Tip — Find Every Wi-Fi Password Saved on Your Machine with Python (10 Lines, No Admin Tools)

Quick Tip — Find Every Wi-Fi Password Saved on Your Machine with Python (10 Lines, No Admin Tools)

Comments
1 min read
I Replaced GitHub Copilot with Continue.dev + a Local Model for 60 Days — My Code Didn't Get Worse, My Wallet Got Happier

I Replaced GitHub Copilot with Continue.dev + a Local Model for 60 Days — My Code Didn't Get Worse, My Wallet Got Happier

Comments
2 min read
I Let Dify Build My AI Workflow for a Week — Then I Replaced Half of It with 80 Lines of Python

I Let Dify Build My AI Workflow for a Week — Then I Replaced Half of It with 80 Lines of Python

Comments
2 min read
Quick Tip — Query a Postgres Database from Python in 6 Lines (No ORM, No Boilerplate)

Quick Tip — Query a Postgres Database from Python in 6 Lines (No ORM, No Boilerplate)

Comments
1 min read
I Ran My Whole Side Project on Cloudflare's Free Tier for 90 Days — AWS Would Have Cost Me $847

I Ran My Whole Side Project on Cloudflare's Free Tier for 90 Days — AWS Would Have Cost Me $847

Comments
2 min read
I Switched from GitHub Copilot to Continue.dev + Ollama for 30 Days — My Code Never Left My Laptop

I Switched from GitHub Copilot to Continue.dev + Ollama for 30 Days — My Code Never Left My Laptop

Comments
2 min read
Quick Tip: Run a Local Vision Model with Ollama in 3 Commands (Free, No API Key)

Quick Tip: Run a Local Vision Model with Ollama in 3 Commands (Free, No API Key)

Comments
2 min read
I Stored 1GB in the Cloud for $0: Cloudflare R2 vs Backblaze B2 vs Storj — One Is Not Like the Others

I Stored 1GB in the Cloud for $0: Cloudflare R2 vs Backblaze B2 vs Storj — One Is Not Like the Others

Comments
2 min read
I Replaced My $20/Month Cursor Subscription with Dify — Saved $240/Year and Got Full Control

I Replaced My $20/Month Cursor Subscription with Dify — Saved $240/Year and Got Full Control

Comments
1 min read
Quick Tip: Run Local LLMs with Ollama + Continue.dev in VS Code (Free Copilot Alternative)

Quick Tip: Run Local LLMs with Ollama + Continue.dev in VS Code (Free Copilot Alternative)

Comments
1 min read
I Ran the Same Inference API on Hugging Face Spaces, Replicate, and Together Free Tiers — One Clear Winner

I Ran the Same Inference API on Hugging Face Spaces, Replicate, and Together Free Tiers — One Clear Winner

Comments
2 min read
I Replaced GitHub Copilot with Tabby — Saved $120/Year and Got My Code Privacy Back

I Replaced GitHub Copilot with Tabby — Saved $120/Year and Got My Code Privacy Back

Comments
1 min read
Quick Tip: Run Any Hugging Face Model Locally with Ollama (One Command)

Quick Tip: Run Any Hugging Face Model Locally with Ollama (One Command)

Comments
1 min read
I Ran the Same Edge Function on Cloudflare Workers, Deno Deploy, and Val.town — One Clear Winner

I Ran the Same Edge Function on Cloudflare Workers, Deno Deploy, and Val.town — One Clear Winner

Comments
2 min read
I Replaced My $50/Month n8n Cloud Bill with Dify — Here's the Free Self-Hosted Setup

I Replaced My $50/Month n8n Cloud Bill with Dify — Here's the Free Self-Hosted Setup

Comments
2 min read
Quick Tip: Host Your ML Demo for Free on Hugging Face Spaces (No Server Needed)

Quick Tip: Host Your ML Demo for Free on Hugging Face Spaces (No Server Needed)

Comments
1 min read
I Ran the Same Serverless DB on Turso, Neon, and Cloudflare D1 — One Clear Winner

I Ran the Same Serverless DB on Turso, Neon, and Cloudflare D1 — One Clear Winner

Comments
2 min read
MiniMax H3 Is Hype Until Your Own Eval Says Otherwise

MiniMax H3 Is Hype Until Your Own Eval Says Otherwise

Comments
2 min read
I Replaced My $240/Year Cursor Subscription with Continue.dev — Here's the Free Setup

I Replaced My $240/Year Cursor Subscription with Continue.dev — Here's the Free Setup

Comments
2 min read
Quick Tip: Run Hugging Face Models on Google Colab's Free GPU (No Local Setup)

Quick Tip: Run Hugging Face Models on Google Colab's Free GPU (No Local Setup)

Comments
2 min read
I Ran the Same KV Workload on Upstash, Redis Cloud, and Self-Hosted Valkey — One Clear Winner

I Ran the Same KV Workload on Upstash, Redis Cloud, and Self-Hosted Valkey — One Clear Winner

Comments
3 min read
Not Every Prompt Deserves a Frontier Model: A Practical Router for LLM Traffic

Not Every Prompt Deserves a Frontier Model: A Practical Router for LLM Traffic

Comments 1
5 min read
I Self-Hosted My AI Coding Stack with Ollama, Continue, and Tabby — Total Cost $0/Month

I Self-Hosted My AI Coding Stack with Ollama, Continue, and Tabby — Total Cost $0/Month

Comments
2 min read
I Ran the Same Fine-Tune on Colab, Kaggle, and Lightning AI Free GPUs — Only One Didn't Waste My Time

I Ran the Same Fine-Tune on Colab, Kaggle, and Lightning AI Free GPUs — Only One Didn't Waste My Time

Comments
2 min read
I Ran the Same Site on Vercel, Netlify, and Cloudflare Pages Free Tiers — One Clear Winner

I Ran the Same Site on Vercel, Netlify, and Cloudflare Pages Free Tiers — One Clear Winner

Comments
3 min read
I Tested 5 Free Database Services — Here's What I Found

I Tested 5 Free Database Services — Here's What I Found

Comments
2 min read
I Ran the Same App on Supabase, Neon, and PlanetScale Free Tiers — One Clear Loser

I Ran the Same App on Supabase, Neon, and PlanetScale Free Tiers — One Clear Loser

1
Comments 4
2 min read
Quick Tip — Python's functools.cache Cut My Script's Runtime by 94%

Quick Tip — Python's functools.cache Cut My Script's Runtime by 94%

Comments
1 min read
I Stopped Paying $25/Month for API Hosting — Cloudflare Workers Runs My Backend for $0

I Stopped Paying $25/Month for API Hosting — Cloudflare Workers Runs My Backend for $0

Comments
2 min read
Dify vs Building with LangChain Yourself — I Shipped the Same RAG App Twice, and the Winner Isn't Close

Dify vs Building with LangChain Yourself — I Shipped the Same RAG App Twice, and the Winner Isn't Close

Comments
2 min read
Quick Tip: Ollama's `OLLAMA_CONTEXT_LENGTH` Env Var — Double Your Local Model's Memory for Free

Quick Tip: Ollama's `OLLAMA_CONTEXT_LENGTH` Env Var — Double Your Local Model's Memory for Free

Comments
2 min read
I Replaced My $15/Month Postgres Bill with Neon's Free Tier — 6 Months Later, Here's the Real Data

I Replaced My $15/Month Postgres Bill with Neon's Free Tier — 6 Months Later, Here's the Real Data

Comments
3 min read
MiniMax H3 Just Dropped — Here's Why It's a Game-Changer

MiniMax H3 Just Dropped — Here's Why It's a Game-Changer

Comments
2 min read
Quick Tip: Chain Multiple Free GPUs in One Day — Colab, Kaggle, and Lightning AI Compared (2026)

Quick Tip: Chain Multiple Free GPUs in One Day — Colab, Kaggle, and Lightning AI Compared (2026)

Comments
2 min read
I Replaced My $50/Month PaaS Bill with Cloudflare Workers + Neon — Here's the Exact Setup

I Replaced My $50/Month PaaS Bill with Cloudflare Workers + Neon — Here's the Exact Setup

Comments
3 min read
A Reproducible Checklist for Evaluating Free AI Coding Models Before You Rely on Them

A Reproducible Checklist for Evaluating Free AI Coding Models Before You Rely on Them

Comments
5 min read
Dify vs n8n: I Replaced a $600/Month Automation Bill With One of Them — and It's Not the One You'd Expect

Dify vs n8n: I Replaced a $600/Month Automation Bill With One of Them — and It's Not the One You'd Expect

Comments
2 min read
Quick Tip: Colab's Free GPU Is 10x Faster Than Your Laptop for LLM Fine-Tuning — Here's the 5-Minute Setup

Quick Tip: Colab's Free GPU Is 10x Faster Than Your Laptop for LLM Fine-Tuning — Here's the 5-Minute Setup

Comments
2 min read
I Ran My Entire Side Project for $0 for 90 Days — The Free Tier Stack That Actually Held Up

I Ran My Entire Side Project for $0 for 90 Days — The Free Tier Stack That Actually Held Up

Comments
2 min read
Continue vs Tabby vs MonkeyCode: I Installed All 3 Free Copilot Alternatives — One Clear Winner

Continue vs Tabby vs MonkeyCode: I Installed All 3 Free Copilot Alternatives — One Clear Winner

Comments
2 min read
loading...