91.4% Token Savings
Verified & Reproducible
Real benchmark with 797 decisions proves Continuity is 11.7× more efficient than embedding decisions in CLAUDE.md. See the math, run the tests yourself.
Token Comparison
Watch the numbers in real-time: CLAUDE.md keeps climbing, Continuity stays flat
Real benchmark with 797 decisions
Token Comparison
The Scaling Problem
CLAUDE.md hits context limits. Continuity scales infinitely.
Token Growth: O(n) vs O(1)
CLAUDE.md grows linearly with decisions. Continuity stays constant.
CLAUDE.md hits the 200K context limit at 674 decisions and becomes unusable.
Continuity handles unlimited decisions while staying at ~20K tokens.
Calculate Your Savings
See exactly how much you'll save based on your project size
Token Savings Calculator
See your savings based on project size
| Metric | CLAUDE.md | Continuity |
|---|---|---|
| Tokens per Session | 150,053 | 20,073 |
| Monthly Token Usage | 90.0M | 12.0M |
| Monthly Cost (@ $3/1M) | $270.10 | $36.13 |
| Complexity | O(n) | O(1) |
| Scalability | Max 674 decisions | Unlimited |
CLAUDE.md: T = 7,053 + (n × 286) = 150,053 tokens | Continuity: T = 20,073 tokens (constant)
CLAUDE.md vs Continuity
They serve different purposes and work best together
CLAUDE.md
Static documentation file
Grows linearly with decisions
•Loads ALL decisions every time
•Manual editing required
•Breaks at 674 decisions
•No search capability
Best for: Project instructions, coding standards, static context (~7,000 tokens)
Continuity
Intelligent memory system
Constant regardless of decisions
•Loads only what you need
•Automatic logging
•Unlimited decisions
•Semantic search
Best for: Decision memory, searchable history, dynamic queries (unlimited decisions)
| Feature | CLAUDE.md | Continuity |
|---|---|---|
| Static project instructions | ||
| Store 100 decisions | ||
| Store 500 decisions | ||
| Store 800+ decisions | ||
| Search specific decisions | ||
| Semantic similarity search | ||
| Log decisions automatically | ||
| Session handoff | ||
| Decision relationships | ||
| Link decisions to code | ||
| Token efficient(O(n) vs O(1)) | ||
| Team collaboration |
Real-World Scenario: "What did we decide about authentication?"
With CLAUDE.md Only
- 1.Claude loads ALL 795 decisions (234K tokens)
- 2.Claude scans through everything manually
- 3.You've used 117% of context before even asking
- 4.Doesn't work - exceeds context limit
With Continuity
- 1.Claude calls
search_decisions("authentication") - 2.Returns only the 5-15 relevant decisions (~4K tokens)
- 3.You've used 10% of context
- 4.Works perfectly, room for long conversations
The Verdict: They Work TOGETHER
Use CLAUDE.md for:
What to do (instructions)
Use Continuity for:
What we decided (memory)
CLAUDE.md and Continuity serve different purposes. They're not replacements—they're complements.
Scaling Projections
Token savings increase as your project grows
| Decisions | CLAUDE.md Tokens | Continuity Tokens | Savings | Status |
|---|---|---|---|---|
| 50 | 21,353 | 20,073 | 6.0% | |
| 100 | 35,653 | 20,073 | 43.7% | |
| 250 | 78,553 | 20,073 | 74.4% | |
| 500 | 150,053 | 20,073 | 86.6% | |
| 674LIMIT | 200,000 | 20,073 | 90.0% | |
| 795ACTUAL | 234,123* | 20,073 | 91.4% | |
| 1,000 | 293,053* | 20,073 | 93.2% | |
| 5,000 | 1,437,053* | 20,073 | 98.6% | |
| 10,000 | 2,867,053* | 20,073 | 99.3% |
Key Insight: Savings increase as your project grows.
The more decisions you log, the more efficient Continuity becomes. At 10,000 decisions, you save 99.3% of tokens.
Mathematical Proof
Formal proof that Continuity provides asymptotically superior token efficiency
| Symbol | Definition | Measured Value |
|---|---|---|
| n | Total number of decisions | 795 |
| d | Average tokens per decision | 286 |
| b | Base CLAUDE.md instructions | 7,053 |
| q | Search queries per session | 3 |
| r | Results returned per query | 15 |
| C | Context window limit | 200,000 |
The Fundamental Equation
As decisions grow, Continuity's relative cost approaches zero.
Q.E.D.
Getting Started
What is Continuity?
Continuity is a RAG-based synthetic memory system for AI coding assistants. It captures architectural decisions, tracks documentation changes, and provides persistent context across sessions - solving the problem of AI assistants "forgetting" previous conversations.
Key Advantage: O(1) Token Efficiency
Unlike CLAUDE.md which loads ALL decisions every session (O(n)), Continuity uses semantic search to retrieve only relevant decisions - keeping token usage constant regardless of project size.
Installation
Option 1: Manual Installation (Recommended)
- Download the latest .vsix file
- Open VS Code
- Press
Cmd/Ctrl+Shift+P - Type "Extensions: Install from VSIX..."
- Select the downloaded file
- Reload VS Code when prompted
First Steps
After installation:
- Run
Continuity: Initializein your project - This creates a
.continuity/folder - Start logging decisions with
@continuity log_decision - View your session handoff with
@continuity session-handoff
Features
Free Tier
Manual capture of architectural decisions
Core MCP resources available
Limited to 5 decisions
Older decisions hidden
Pro Features
Upgrade to ProSmart, immediate, and review modes
AI-powered context retrieval (O(1) efficiency)
Interactive D3.js visualization
No storage limits - scale to 10,000+
4-layer intelligent filtering
CSV, JSON, Markdown formats
License Management
Activation
After purchasing, you'll receive a license key via email. Activate it in VS Code:
- Press
Cmd/Ctrl+Shift+P - Type "Continuity: Activate License"
- Enter your license key and email
License Types
Renews monthly, cancel anytime
Renews annually, save 23% vs monthly
Never expires, all future updates included
MCP Integration
What is MCP?
Continuity integrates with the Model Context Protocol (MCP) to provide AI assistants like Claude, Cursor, and Cline with persistent memory and decision logging capabilities.
Available MCP Resources
@continuity log_decisionLog architectural decisions with question, answer, and optional tags
@continuity search_decisionsSearch logged decisions by keyword or semantic query - O(1) efficiency
@continuity session-handoffGet complete project context including recent decisions and documentation status
API Reference
License Validation
POST /api/licenses/validate{
"license_key": "12345678-90ab-cdef-1234-567890abcdef",
"device_id": "device-uuid",
"device_name": "MacBook Pro",
"platform": "darwin",
"vscode_version": "1.84.0",
"extension_version": "3.9.7"
}Device Management
POST /api/devices/activateActivate a new device for a license
DELETE /api/devices/:device_idDeactivate a device
Troubleshooting
License activation fails
- Verify your license key is correct (check for typos)
- Ensure you're using the email from your purchase
- Check your internet connection
- Contact support if issue persists
MCP integration not working
- Verify Continuity is installed and activated
- Check that your AI assistant supports MCP
- Restart your AI assistant application
- Check MCP server logs in VS Code Output panel
Need more help? Email us at [email protected] with your license key and a description of the issue.
Frequently Asked Questions
Why is Continuity more efficient than CLAUDE.md?
CLAUDE.md loads ALL decisions into context every session (O(n) complexity - grows linearly). Continuity uses semantic search to retrieve only relevant decisions (O(1) complexity - constant). At 795 decisions, this means 234K tokens vs 20K tokens - a 91.4% reduction.
What happens when I have more than 674 decisions?
CLAUDE.md cannot work beyond 674 decisions - it exceeds Claude's 200K context window. Continuity handles unlimited decisions because it only loads ~20K tokens regardless of how many decisions you have.
How much money will I save?
Based on real benchmarks with 795 decisions and 600 sessions/month: CLAUDE.md costs $421/month while Continuity costs $36/month. That's $385/month or $4,623/year in savings.
Is my data secure?
Yes. All decisions are stored locally in your project's .continuity/ folder. License validation uses encrypted HTTPS connections, and we never store your decision data on our servers.
What AI assistants does Continuity work with?
Continuity works with any AI assistant that supports the Model Context Protocol (MCP), including Claude Code, Cline, Cursor, Roo Code, and more. It also works standalone in VS Code.
Still have questions?
Our team is here to help. Reach out via email or check our activation guide for step-by-step instructions.