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

Jina AI
Jina AI
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
B
Blog
T
The Blog of Author Tim Ferriss
量子位
Microsoft Azure Blog
Microsoft Azure Blog
博客园 - Franky
小众软件
小众软件
Recent Announcements
Recent Announcements
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
I
InfoQ
美团技术团队
G
Google Developers Blog
Engineering at Meta
Engineering at Meta
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
V
Visual Studio Blog
云风的 BLOG
云风的 BLOG
博客园 - 【当耐特】
IT之家
IT之家
Microsoft Security Blog
Microsoft Security Blog
博客园 - 聂微东
Last Week in AI
Last Week in AI
H
Hackread – Cybersecurity News, Data Breaches, AI and More
H
Help Net Security

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
Chat Wizard - a VS Code extension to serve as the AI chat...
Avraham · 2026-05-29 · via DEV Community

Avraham

Chat Wizard - a VS Code extension to serve as the AI chats memory layer
After embracing the AI ride months ago and turning into an avid user of Claude and GitHub Copilot (while experimenting with Cline, Cursor and Google Antigravity on the way), I kept running into the same kind of friction:

Some concrete situations:

  1. “I remember working on something similar 2 weeks ago…” But I don’t remember which session it was.

→ Chat Wizard adds full-text search across chat sessions, so you can locate them by content

  1. Revisiting an old discussion with new context Example: I compared a certain architecture before, and now I’ve found new drawbacks I want to factor in.

The usual flow:

  • find the chat
  • copy parts of it
  • paste into a new session
  • add new input

→ The extension lets you search for the session and inject it into a new chat, avoiding manual copy/paste

  1. Repeated topics across multiple chats Some topics come up every few days, but:
  • they’re spread across sessions
  • wording differs
  • search isn’t always reliable

→ You can tag sessions and filter by tag
→ There’s also topic similarity search to surface related conversations

  1. “I got that code snippet the other day… I need it again” But I don’t remember where it was generated.

→ Chat Wizard provides a Code Snippets view to quickly find previously generated code

  1. Getting a sense of model usage When switching between models, it’s not obvious how usage is distributed.

→ The extension includes a model usage panel

  1. Repeated prompts / patterns Sometimes it feels like I’m asking the same things again and again.

→ There’s a Prompts Library that groups similar prompts, shows counts, and links to the sessions where they were used

  1. Finding chats by topic, not just keywords Even with search, some relevant sessions don’t share exact terms.

→ Topic similarity + the queryHistory MCP tool help retrieve those

Overall goal is simple:

  • make past chats easier to find
  • make them easier to reuse
  • give some visibility into how they’re used over time

Curious how others deal with this:

  • What’s your biggest pain with AI coding tools today?
  • Do you actually go back to old AI chats, or do you just start fresh every time?
  • What would make this a must-have for you?

Repo:
https://github.com/Veverke/ChatWizard

VS Code Marketplace:
https://marketplace.visualstudio.com/items?itemName=Veverke.chatwizard

VSX Org Marketplace:
https://open-vsx.org/extension/Veverke/chatwizard

Would appreciate feedback, especially from people using AI heavily inside VS Code.