True-Mem

A persistent memory plugin for OpenCode with cognitive psychology-based memory management.

Table of Contents

• Overview
• The Problem
• The Solution
• The Psychology Behind It
• Key Features
• Installation
• Usage
• Architecture
• Memory Classifications
• Technical Details
• Inspiration
• Debug

Overview

True-Mem is a production-ready memory plugin for OpenCode that enables AI coding agents to remember information across sessions and projects. It doesn't just store information - it manages memory like a human mind would.

The Problem

If you've ever had to repeat your preferences to your AI assistant every time you start a new session, you know the pain. "I prefer TypeScript over JavaScript", "Never use var", "Always run tests before committing" - things you've already said, but the AI forgot.

The Solution

True-Mem automatically extracts and stores memories from your conversations:

• Preferences: "I prefer functional style over OOP"
• Constraints: "Never use var keyword"
• Decisions: "We decided to use SQLite instead of Postgres for this project"
• Bugfixes: "Fixed the auth timeout issue"
• Learning: "Learned that bun:sqlite is built-in"

Next time you open OpenCode, it remembers. No more repeating yourself.

The Psychology Behind It

What makes True-Mem different from a simple database? It's modeled after how human memory actually works:

Ebbinghaus Forgetting Curve - Episodic memories fade over time (7-day default), while preferences and decisions stay permanent. Just like your brain forgets what you had for lunch last Tuesday but remembers your favorite color.

7-Feature Scoring Model - Every memory is scored using Recency, Frequency, Importance, Utility, Novelty, Confidence, and Interference. This determines which memories surface when you need them.

Dual-Store Architecture (STM/LTM) - Short-term and long-term memory stores with automatic promotion. High-strength memories get promoted to LTM; weak ones stay in STM or decay.

Four-Layer Defense System - Prevents false positives with Negative Pattern filtering (including AI meta-talk detection), Multi-Keyword Scoring, Confidence Thresholds, and Role Validation (only Human messages for user-level preferences).

Reconsolidation - When new information conflicts with existing memories, the system detects similarity and handles it intelligently (merge duplicates, keep both complements, or resolve conflicts).

Jaccard Similarity Search - Fast, lightweight semantic retrieval without heavy ML dependencies.

Key Features

Installation

npm install true-mem

Then add to your ~/.config/opencode/opencode.jsonc:

{
  "plugin": [
    "true-mem"
  ]
}

Usage

Automatic Extraction

Just have conversations with OpenCode. True-Mem extracts relevant info in the background.

What gets stored:

• User preferences: "I prefer TypeScript over JavaScript"
• Constraints: "Never use var keyword"
• Decisions: "We decided to use SQLite instead of Postgres"
• Bugfixes: "Fixed null pointer in auth module"
• Learning: "I learned that bun:sqlite is built-in"

Explicit Memory Storage

Use phrases like "Remember this:" or "Ricorda questo:" to force storage:

"Ricorda questo: preferisco sempre usare TypeScript per i miei progetti"
"Remember this: never commit without running tests first"

Architecture

true-mem/
├── src/
│   ├── index.ts                 # Entry point with fire-and-forget init
│   ├── storage/
│   │   ├── sqlite-adapter.ts    # bun:sqlite + node:sqlite runtime adapter
│   │   └── database.ts          # MemoryDatabase class
│   ├── memory/
│   │   ├── patterns.ts          # Multilingual patterns (15 languages)
│   │   ├── negative-patterns.ts # False positive prevention
│   │   ├── role-patterns.ts     # Role-aware extraction (Human vs Assistant)
│   │   ├── classifier.ts        # Four-layer defense + role validation
│   │   ├── embeddings.ts        # Jaccard similarity
│   │   └── reconsolidate.ts     # Conflict resolution
│   ├── extraction/
│   │   └── queue.ts             # Fire-and-forget extraction queue
│   └── adapters/
│       └── opencode/
│           └── index.ts         # Full extraction + injection
└── dist/
    └── index.js                 # Bundle (~92KB)

Memory Classifications

Technical Details

7-Feature Scoring Model

Strength Formula: Strength = Sum(weight_i * feature_i) clamped to [0, 1]

Four-Layer False Positive Prevention

Decay Strategy

• Episodic memories: Decay using Ebbinghaus formula (lambda = 0.05 STM, 0.01 LTM)
• All other types: Permanent (no decay)

Inspiration

This project was inspired by PsychMem - a pioneering plugin for persistent memory in OpenCode. True-Mem builds on those ideas with a focus on cognitive psychology models and production stability.

Debug

# View logs
tail -f ~/.true-mem/plugin-debug.log

# Query database
sqlite3 ~/.true-mem/memory.db "SELECT classification, summary, strength FROM memory_units WHERE status = 'active' ORDER BY strength DESC LIMIT 10;"

Version: 1.0.0
License: MIT
Status: Production-ready, actively maintained