secondmind

# SecondMind – Autonomous AI Memory, Initiative & Social Intelligence

## When To Use
Activate this skill when the user:
- Asks to set up, configure, or check SecondMind status
- Wants to search their knowledge base or recall past conversations
- Asks for proactive suggestions or project ideas
- Mentions memory, remembering, or context from past sessions
- Sends /new or /reset (trigger pre-reset flush!)
- Asks about their mood/emotional patterns or upcoming events
- Sends any SecondMind Telegram command (see below)

## First-Run Setup
If the database does not exist at `{baseDir}/data/secondmind.db`:
```bash
node {baseDir}/setup.js
```
Then guide the user through editing `{baseDir}/config.json`:
1. Set `openrouter.apiKey` (required – get one at https://openrouter.ai/keys)
2. Check `openclaw.sessionsDir` matches their agent's session path
3. Optional: Enable Telegram notifications

## CRITICAL: Pre-Reset Memory Capture
When the user sends /new or /reset:
1. BEFORE the reset takes effect, run:
   ```bash
   node {baseDir}/scripts/flush.js
   ```
2. Respond with the script's output (e.g. "💾 Session archived.")
3. THEN allow the reset to proceed normally

## Telegram Commands (Integrated Mode)
When `telegramMode` is `"integrated"` in config.json, the OpenClaw agent handles
these commands directly. Execute the corresponding script and format the response.

### /smstatus or /es
```bash
node {baseDir}/scripts/status.js
```

### /proposals or /ep [filter]
```bash
node {baseDir}/scripts/proposals.js [proposed|accepted|rejected|all]
```

### /accept <ID...> [comment] or /ea <ID...> [comment]
```bash
node {baseDir}/scripts/feedback.js accept <ID...> [comment]
```
Supports multiple IDs: `/accept 1 3 5` or `/accept all`
After accepting, a **project is automatically created** to track progress.
1. Read the proposal's `follow_up` field from the database:
   `sqlite3 {baseDir}/data/secondmind.db "SELECT follow_up, description FROM proposals WHERE id=<ID>"`
2. If there's a follow_up...

# 🧠 SecondMind – Autonomous AI Memory & Proactive Initiative for OpenClaw

> **Made by AI, for AI** – An OpenClaw skill that gives your agent persistent memory, emotional awareness, and the ability to think ahead.

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
[![Node.js](https://img.shields.io/badge/Node.js-18%2B-green.svg)](https://nodejs.org)
[![OpenRouter](https://img.shields.io/badge/API-OpenRouter-purple.svg)](https://openrouter.ai)

**SecondMind** transforms your OpenClaw agent from a reactive tool into a **proactive team member** that remembers everything, detects your mood, and suggests helpful actions before you even ask.

Created by **Emphaiser** – not a programmer, but a tinkerer who built this entirely with the help of AI. If AI can build its own memory system, that's pretty meta. 🤖

---

## ✨ Features

- **Three-Tier Memory**: Short-term buffer → Mid-term structured knowledge (FTS5) → Long-term archive (FTS5)
- **Proactive Initiative**: Analyzes your knowledge base every 6 hours and suggests automations, fixes, and project ideas
- **Semantic Deduplication**: 3-stage pipeline (Hash → FTS Prefilter → LLM Judge) prevents repeated suggestions
- **Social Intelligence**: Detects frustration, stress, excitement – reminds you of events, offers help during stressful times
- **Project Tracking**: Accepted proposals become tracked projects – no more repeat suggestions for completed work
- **Archive Retrieval**: Long-term memory is actively used when generating new suggestions ("Remember when we solved this before?")
- **Bulk Feedback**: Accept, reject, or permanently drop multiple proposals at once – even using natural language
- **Telegram Integration**: Push notifications + full feedback control directly in Telegram
- **Gentle Reminders**: Deferred proposals get nudges after a cooldown, stalled tasks get check-ins
- **Auto-Throttle**: Too many rejections? The engine backs off automatically
- **100% Cloud**: All models via [Ope...