context-optimizer

# OpenClaw Context Optimizer

**Reduce context/token usage by 40-60% through intelligent compression and learning.**

## What is it?

The first OpenClaw skill that **intelligently compresses context** to reduce token costs by 40-60%. Uses multiple strategies (deduplication, pruning, summarization) and learns what context matters over time. Works seamlessly with Memory System for maximum efficiency.

## Key Features

- ⚡ **40-60% Token Savings** - Intelligent compression without information loss
- 🧠 **Learning System** - Adapts to what context matters in your workflow
- 🔄 **Multiple Strategies** - Dedup, prune, summarize, hybrid
- 💾 **Memory Integration** - Works with OpenClaw Memory System
- 💰 **x402 Payments** - Agents can pay for unlimited compressions (0.5 USDT/month)
- 📊 **ROI Tracking** - Automatically calculates return on investment

## Free vs Pro Tier

**Free Tier:**
- 100 compressions per day
- All compression strategies
- Basic statistics and ROI tracking

**Pro Tier (0.5 USDT/month):**
- Unlimited compressions
- Advanced learning algorithms
- Priority compression
- Detailed analytics
- Custom compression rules

## Installation

```bash
claw skill install openclaw-context-optimizer
```

## Commands

```bash
# Compress context manually
claw optimize compress "Long context..." --strategy=hybrid

# Show compression stats
claw optimize stats

# View compression history
claw optimize history --limit=10

# Calculate ROI
claw optimize roi

# Open dashboard
claw optimize dashboard

# Subscribe to Pro
claw optimize subscribe
```

## How It Works

1. **Hooks into requests** - Automatically intercepts context before API calls
2. **Analyzes content** - Identifies redundant, irrelevant, or summarizable info
3. **Applies strategy** - Deduplication → Pruning → Summarization
4. **Learns patterns** - Tracks what context was useful vs. wasted
5. **Compresses intelligently** - Reduces tokens by 40-60%...

# OpenClaw Context Optimizer

**Reduce context/token usage by 40-60% through intelligent compression and learning.**

Stop burning tokens on redundant context. Context Optimizer intelligently compresses conversation history, deduplicates information, and learns what context actually matters - all while seamlessly integrating with OpenClaw Memory System.

🤖 **Agent-powered economy** - agents can autonomously pay 0.5 USDT/month for unlimited compressions. [Agent Payments →](AGENT-PAYMENTS.md)

## The Problem

OpenClaw users are experiencing:
- 💸 **High token costs** - sending full context every request
- 🔄 **Redundant information** - same facts repeated across messages
- 📈 **Growing context** - conversations balloon to 10K+ tokens
- 🐌 **Slower responses** - large contexts slow down API calls
- 💰 **Wasted money** - paying for unused/irrelevant context

## The Solution

**Intelligent context compression that reduces token usage by 40-60% without losing important information.**

## Features

- ✅ **Smart Compression** - Reduces context size by 40-60%
- ✅ **Multiple Strategies** - Deduplication, pruning, summarization, hybrid
- ✅ **Memory Integration** - Works seamlessly with OpenClaw Memory System
- ✅ **Learning System** - Adapts to what context matters over time
- ✅ **Quota Management** - Free tier (100 compressions/day) + Pro tier (unlimited)
- ✅ **Statistics & ROI** - Track savings and calculate return on investment
- ✅ **Web Dashboard** - Visual interface for compression stats and configuration
- ✅ **CLI Interface** - Full control from command line
- 🤖 **x402 Agent Payments** - Agents can autonomously pay for Pro tier (0.5 USDT/month)

## Why Context Optimizer?

**The ONLY OpenClaw tool that intelligently compresses context to reduce token costs.**

| Feature | Context Optimizer | Manual Summarization | Generic Compression | Memory System Alone |
|---------|-------------------|----------------------|----------------...