SKULLFIRE07/cortex-memory

> **Your AI forgets everything between sessions. Cortex gives it a brain.**
Every time you start a new AI coding session, you waste 15-30 minutes re-explaining your project. Architecture, past decisions, known bugs, conventions — all gone.
**Cortex captures everything automatically** and injects it into your next session before you type a single character.
Works with **Claude Code** | **Cursor** | **Cline** | **Copilot** | **Any MCP client**
---
Why Cortex?
| Without Cortex | With Cortex |
|---|---|
| "Here's my project structure again..." | AI already knows your architecture |
| "We decided to use Redis because..." | Decision auto-captured with full context |
| "The bug was in the auth middleware..." | Bug pattern recorded, never repeated |
| "Don't touch that file, it's..." | Convention remembered across sessions |
| 15-30 min context loading per session | **0 min.** Full context injected automatically |
---
How It Works
Claude Code, Cursor, and Cline read CLAUDE.md natively.
---
Quick Start
1. Install
Search **"Cortex Memory"** in VS Code Extensions, or:
2. (Optional) Add a free API key for smarter extraction
- Get a free Gemini key at aistudio.google.com/apikey
- Run Ctrl+Shift+P → **Cortex: Set API Key** → paste key
3. Code
Start coding with your AI assistant. Cortex runs silently in the background.
> Works without an API key too — basic pattern-matching extraction runs locally.
---
What Gets Captured
| Signal | Example | Where It's Stored |
|--------|---------|-------------------|
| **Decisions** | "Let's go with Redis for sessions" | decisions.md (ADR format) |
| **Bug patterns** | "Root cause was a race condition" | Episode + working memory |
| **Architecture** | "Refactor auth into its own module" | Episode + decision log |
| **File changes** | Every file read, edited, created | Tracked per episode |
| **Session context** | What you worked on, what's next | Working memory |
| **Open problems** | Unresolved bugs, TODOs | Working memory |
---
LLM Providers
| Provider | Cost | Setup |
|----------|------|-------|
| **Gemini** (default) | **Free** (500 req/day) | Get key at aistudio.google.com/apikey |
| **Anthropic** | ~$0.01/session | Set cortex.apiKey in settings |
| **Ollama** | Free (local) | Install Ollama, set provider to ollama |
| **No API key** | Free | Works with basic pattern matching |
---
CLI Tool
MCP Server (Cursor, Cline, Zed)
Tools: cortex_get_context | cortex_search | cortex_save_memory | cortex_get_decisions | cortex_status
---
Settings
| Setting | Default | Description |
|---------|---------|-------------|
| cortex.llmProvider | gemini | Provider: gemini, anthropic, ollama |
| cortex.apiKey | — | API key for Gemini or Anthropic |
| cortex.maxWorkingMemoryTokens | 800 | Token budget for working memory |
| cortex.autoInjectClaudeMd | true | Auto-inject into CLAUDE.md |
Commands
| Command | Description |
|---------|-------------|
| **Cortex: Set API Key** | Configure your LLM API key |