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

P
Proofpoint News Feed
G
Google Developers Blog
Jina AI
Jina AI
罗磊的独立博客
李成银的技术随笔
爱范儿
爱范儿
WordPress大学
WordPress大学
雷峰网
雷峰网
博客园 - Franky
V
Visual Studio Blog
Recorded Future
Recorded Future
量子位
V
V2EX
阮一峰的网络日志
阮一峰的网络日志
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
博客园_首页
F
Fox-IT International blog
Last Week in AI
Last Week in AI
人人都是产品经理
人人都是产品经理
Recent Announcements
Recent Announcements
F
Future of Privacy Forum
月光博客
月光博客
Security Latest
Security Latest
宝玉的分享
宝玉的分享
P
Privacy International News Feed
O
OpenAI News
IntelliJ IDEA : IntelliJ IDEA – the Leading IDE for Professional Development in Java and Kotlin | The JetBrains Blog
IntelliJ IDEA : IntelliJ IDEA – the Leading IDE for Professional Development in Java and Kotlin | The JetBrains Blog
L
LINUX DO - 热门话题
C
Cyber Attacks, Cyber Crime and Cyber Security
T
Tor Project blog
小众软件
小众软件
P
Privacy & Cybersecurity Law Blog
C
Cisco Blogs
Project Zero
Project Zero
IT之家
IT之家
Y
Y Combinator Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
Microsoft Security Blog
Microsoft Security Blog
B
Blog
博客园 - 【当耐特】
The Register - Security
The Register - Security
J
Java Code Geeks
AWS News Blog
AWS News Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - 聂微东
H
Hacker News: Front Page
Cisco Talos Blog
Cisco Talos Blog
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
博客园 - 三生石上(FineUI控件)

DEV Community

What I Actually Build: AI Systems That Ship, Not Demos That Impress The Box Ticked While You Read This: LinkedIn, AI Training, and the Switch You Did Not Flip Stop Reviewing Every Line of AI Code - Build the Trust Stack Instead How To Build an Image Cropper in Browser (Simple Steps) I built a macOS disk cleaner for developers and just launched it would love feedback Membangun Kompetensi dan Relasi: Mengapa Ekosistem Kampus Itu Penting I Built an AI That Decides Which AI to Talk To — Running 24/7 From My Living Room Codex Team Usage SOP How to Actually Become a Programmer: The Hard Part Nobody Wants to Explain Building a Production-Style Multi-Tool AI Agent with Python, Flask, React & Gemini AI The Caretaker Sandbox: An Offline-First Visual Playground & Template Engine powered by Gemma 4 # Building Instagram OSINT Projects with HikerAPI Your AI can read. Gemma 4 can see The Battle of the Senior Dev: Why AI Gives You Wings But Only If You're Ready to Pilot HiDream Raw Output Failed Tried Dev-2604 VRAM Math Killed It Won with a Prompt Enhancer Instead I Finally Finished a Project I Abandoned — And GitHub Copilot Helped Me Ship It SafeSMS: On-Device Threat Detection with Gemma 4 E4B, no internet required I Built OpenKap — A Loom Alternative for Small Teams Who Just Want to Ship Gemma 4 is Here: The Dawn of Local Multimodal Reasoning Offline-First Flutter: How We Built a CRM That Manages 100K+ Leads With No Internet Memory for Agents: When Vectors Meet Graphs, Bugs Drop 4 The Rise of Production-Grade AI Infrastructure I ran my idea-validation product through its own validator. The verdict was PIVOT. We Built an Agent Commerce API. Google I/O 2026 Changed Our 3-Month Roadmap in 24 Hours. "My Partner's Memory Was Full. I Didn't Know — Until We Tried to Talk." I’m a Front End Web Developer Learning Machine Learning From Scratch Laravel Waiting Request I Built a Chrome Extension to Track How Long You Actually Spend on Each Tab Why Google Can't See Your React Breadcrumbs (And the 4-Line Fix) AI Travel Assistant Powered by Gemma 4; With Streaming, Image Input, and Visual Recommendation Cards Microsoft tried to kill the printer driver. Healthcare said no. The Blueprint Beneath the Blueprint: Designing Data Model and Choosing Its Database REST APIs vs Webhooks in Telecom Billing - Which One Actually Makes Sense? Accounting Made Simple: AI-Powered Financial Insights of Japanese Companies with Gemma 4 The append-only AST trick that makes Flutter AI chat actually smooth Designing the Future of Payments — Why XML Still Matters in the Age of APIs From Legacy to Live — Reviving XMLPayments with GitHub Copilot Two Weeks Into Learning Solana XMLPayments — The Hidden Backbone of Modern Financial Orchestration AI Agents in Practice — Read from the beginning Reviving My Gemma Agentic Framework: From Prototype to Polished Repo Smart Contracts Demand Better Infrastructure: Building on contract.dev Self-Hosted LLM Tool Calling: Forge and the Build-vs-Buy Decision ORA-00072 오류 원인과 해결 방법 완벽 가이드 OpenWA for CTOs: Self-Hosted WhatsApp Gateway Trade-Offs NotebookLM Automation With notebooklm-py: Useful, But Classify Data First Docker v29.5.x Operator Upgrade Checklist Coding-Agent Instruction Design: The CLAUDE.md File That Prevents Rework When I Finally Realized My Runtime Was Holding Me Back GnokeOps: Host Your Own AI House Party The Death of Static Rate Limiters: Why Your Java Virtual Threads Need BBR-Style Adaptive Concurrency AI Agents in Practice — Part 2: What Makes Something an Agent Stop scattering LLM SDK/API calls across your codebase. Here is the 2-file rule that fixed mine Beyond Prompts: Structuring AI Workflows for Real Frontend Engineering From an Abandoned Hackathon Project to an AI Study Workspace 🚀 Terraform with AI: Build AWS Infra (Cursor + MCP) What If AI Didn’t Need the Internet? 750,000 Chips, 140 Trillion Tokens: The Math Behind DeepSeek's Permanent Price Cut You're Renting Someone Else's Compute — And It's Costing You More Than You Think CSS :has() Selector: The Layout Trick I Wish I Knew 5 Years Ago Five Clusters. Five Lessons. One Production System. Synaptic: A Local-First AI Dev Companion That Remembers How You Think Revolutionizing Edge MedTech: Building a Sovereign Sleep Apnea Companion ("XiHan Snore Coach") with Gemma 4 HDD Eksternal Tiba-Tiba Tidak Bisa Diakses di Windows? Ini Tiga Lapis Fix-nya DMARC p=none vs p=quarantine vs p=reject: what to use and when DSA Application in Real Life: How Git Diff Works: LCS Intuition, Myers Algorithm, and Real Code Changes I solo-built a reputation layer for AI agents on NEAR — and here's what I learned I built an AI faceless video generator in 2 months — here's the stack Diffusion Language Models: How NVIDIA Nemotron-Labs Diffusion Shatters the Autoregressive Speed Ceiling llm-nano-vm v0.8.0 — deterministic FSM runtime for LLM pipelines, now with output validation and per-step timeouts From the Renaissance to the Quantum Dawn: AI, Computation, and the Next Paradigm Shift How I Built a Review Site with 800+ Articles Using AI I Built a Smart Kitchen AI with Gemma 4 That Turns Fridge Photos Into Recipes Why your vulnerability dashboard is lying to you (and how to fix it) From Abandoned Prototype to Smart AI System: Reviving Trafiq AI with GitHub Copilot Why Country/State/City Pickers Are Weirdly Hard Node.js 22 LTS — EOL Date, Support Timeline, and What Comes Next The 7-Layer Memory Architecture Behind Modern AI Agents I Imagined Hermes Agent Running an Entire Smart City — And It Changed How I See AI One backend, four products: why we bet on platform-per-brand AI's tech debt is invisible — even to AI. I solved it at the architecture layer. Why ROAS 300% Can Still Mean Losses — Gross Margin in 5 Ecommerce Verticals You Don’t Need to Try Every AI Tool to Keep Up NovelPilot: A Novel Writing Agent Powered by Gemma 4 BoxAgnts is an Out-Of-The-Box Secure AI Agent ToolBox in a WASM SandBox Gemma 4 deep dive: why a 1.5 GB model scores 37.5% on competition mathematics, how the MoE routing actually works, and which model fits your hardware. Full breakdown inside. BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090 Google Just Declared the Chat-Log Interface Dead. Here's What Neural Expressive Actually Signals for Developers. ARCHITECTURE SPECIFICATION & FORMAL SYSTEM REPORT: k501-AIONARC Notes from a Hammock What's Google Antigravity 2.0 ? Here's What the Agent Harness Actually Changes for Developers. Building an E2EE Chat App in Flask - Part 3: Keeping File Uploads Safe Google's Gemini Spark. Here's What It Actually Does for Developers. Microsoft Just Shipped MCP Governance for .NET. Here's What It Actually Enforces. How I Built a Pakistan Internet Speed Test Platform at 16 How to Build a Supervisor Agent Architecture Without Frameworks I Built My Own Corner of the Internet — Here's What It Looks Like How does VuReact compile Vue 3's defineExpose() to React? Neo-VECTR's Rift Ascent Idempotency Keys: The API Safety Net You Probably Aren't Using
I Cancelled My $20 Claude Cowork Plan After a Week With OpenWork
Sergei Peles · 2026-05-23 · via DEV Community

Sergei Peleskov

I Cancelled My $20 Claude Cowork Plan After a Week With OpenWork

I didn't expect to cancel. I'd been paying for Claude Cowork, it worked, and switching tools is usually more hassle than it's worth. Then I spent a week running OpenWork — open-source, free — on actual work instead of a toy demo. By Friday I'd cancelled the plan.

Here's the honest version of what happened, including the part that nearly made me quit on day one.

The setup that took two minutes

I went in skeptical. Free open-source agent clients usually mean "free, but you'll spend a weekend configuring it." OpenWork wasn't that.

It ships with a provider called OpenCode Zen, and there are five free models sitting in the selector before you sign into anything — DeepSeek V4 Flash, Qwen3.6 Plus, MiniMax M2.5, and two more. No card, no subscription. I picked DeepSeek, handed it a refactor task on a real repo, and it generated the diff, applied it, tests green on the first run.

That was the moment the skepticism dropped. Same task in Cowork needs the $20 plan. Same machine, two windows, one charges and one doesn't.

The thing that actually sold me

It wasn't the free models. It was MCP setup.

If you've added an MCP server to Claude Cowork, you know the drill: open the JSON config, find the right format, paste the server command, restart, hope it loads. I'd timed it once — about twenty minutes for five tools the first time.

In OpenWork it's a tile with a Connect button. Notion, Linear, Sentry, Stripe, Context7 — tap, OAuth, done. All five connected in under three minutes. No JSON. That's the whole story. After fighting config files for months, that one button is what made me close the Cowork tab.

The part I didn't see coming

You can tell the agent to drive its own UI. I typed "open Settings, then go to Appearance" and watched the panel open and the tab switch with my hands off the mouse. It sounds like a gimmick until you see it work — it's the demo every assistant vendor has been promising for two years, actually running in something I installed today.

Caveat, because I'm not going to oversell it: this works on the OpenCode Zen models. Point it at Gemini Flash and it falls back to browser tools instead of clicking the native UI. So the free-model story and this feature line up on Zen specifically.

The part that nearly made me quit

Day one, fresh Windows machine, the UI Control feature crashed with a cryptic Bun runtime error. No explanation. The installer never told me it needed Node.js.

I lost an hour to this, so here's the fix so you don't:

  1. Install Node.js from nodejs.org.
  2. Close OpenWork through Task Manager, not the X button — there's no tray icon and the normal close leaves the process alive, so the next launch reuses the broken state.
  3. Relaunch. It works.

That's the kind of thing that makes people uninstall and write a bad review. It's a five-minute fix once you know it, and it's documented nowhere.

Would I tell you to switch?

If you need deep terminal control, Claude Code and Cowork still earn their place. But if you want the no-terminal, get-things-done workflow without a subscription and without being married to one model provider — OpenWork covers it, and it covers it well.

The thing I keep thinking about isn't OpenWork specifically. It's that open-source dev tooling is catching the paid tier on workflow now, not just undercutting on price. That gap closing from the open-source side is the real story.

Tested on a fresh Windows 11 install. Not sponsored. There's one task where OpenWork still loses to paid Claude — saving that for the next one.