Your AI Never Forgets: Introducing Cachly Brain IDE Plugins

The Problem: AI Assistants Have Amnesia

Every time you start a new chat with Copilot, Claude, or Cursor, it starts from scratch. That bug you fixed last week? It'll research it all over again. The deploy command that finally worked? Forgotten.

This costs you: time re-explaining context every session, tokens paying for the same research twice, and sanity watching your AI make the same mistakes again.

The Solution: A Persistent Brain

Cachly Brain is a persistent memory layer for AI coding assistants. It works through the Model Context Protocol (MCP) — an open standard that lets AI tools share context.

Here's how it works:

1. Your AI learns — after fixing a bug, it calls learn_from_attempts("deploy:api", "success", "nohup docker compose up -d --build")
2. Your AI remembers — next session, it calls recall_best_solution("deploy:api") and gets the working command instantly
3. You see everything — our IDE plugins show lesson count, recall stats, and token savings in real-time

What the Plugins Show

Status Bar

A persistent 🧠 Brain: 13 lessons widget in your status bar. One glance tells you if your brain is healthy.

Brain Health Panel

Click the widget and see:

Lesson Viewer

See every lesson your AI has learned:

Each recall saves ~1,200 tokens by reusing a known solution instead of re-researching from scratch.

How Token Savings Work

When your AI starts a session, it calls session_start(). The brain returns relevant lessons for the task at hand. Without the brain, the AI would need to:

• Read multiple files to understand context (~500 tokens)
• Search for similar problems (~300 tokens)
• Try approaches that failed before (~400 tokens)

With the brain, it gets the working solution in one call (~50 tokens). That's ~1,200 tokens saved per recall.

Over time, this compounds. A team of 5 developers with 100+ lessons can save thousands of dollars per month in API costs — and hours of wasted time.

Get Started

VS Code

Install directly from the VS Code Marketplace — search for Cachly Brain — or via the command line:

code --install-extension cachly-dev.cachly-brain

IntelliJ

Settings → Plugins → Marketplace → search Cachly Brain → Install

Configure

1. Get your API key from cachly.dev
2. Set cachly.apiKey and cachly.instanceId in settings
3. Done — the status bar updates automatically