Mathematically Proven

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.

91.4%
Token Savings
11.7×
More Efficient
O(1)
Complexity
$4,623
Yearly Savings

Token Comparison

Watch the numbers in real-time: CLAUDE.md keeps climbing, Continuity stays flat

Real benchmark with 797 decisions

Token Comparison

CLAUDE.md Approach
234,147
tokens per session
Loads ALL decisions every time
Continuity Approach
20,073
tokens per session
Loads only what you need
91.4%
Token Savings
11.7x
More Efficient
214,074
Tokens Saved
CLAUDE.md: O(n) - grows linearly
Continuity: O(1) - constant

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.

0K50K100K150K200K250K300K02505007501000Number of DecisionsTokens200K Context LimitCLAUDE.md BREAKS
CLAUDE.md (O(n) - Linear Growth)
Continuity (O(1) - Constant)
Context Window Limit (200K)

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

505002,000
1006002,000
Token Savings
86.6%
Efficiency
7.5x
Monthly Savings
$234
Yearly Savings
$2808
MetricCLAUDE.mdContinuity
Tokens per Session150,05320,073
Monthly Token Usage90.0M12.0M
Monthly Cost (@ $3/1M)$270.10$36.13
ComplexityO(n)O(1)
ScalabilityMax 674 decisionsUnlimited

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

.md

CLAUDE.md

Static documentation file

Token CostO(n)

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)

C

Continuity

Intelligent memory system

Token CostO(1)

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)

FeatureCLAUDE.mdContinuity
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. 1.Claude loads ALL 795 decisions (234K tokens)
  2. 2.Claude scans through everything manually
  3. 3.You've used 117% of context before even asking
  4. 4.Doesn't work - exceeds context limit
With Continuity
  1. 1.Claude calls search_decisions("authentication")
  2. 2.Returns only the 5-15 relevant decisions (~4K tokens)
  3. 3.You've used 10% of context
  4. 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

DecisionsCLAUDE.md TokensContinuity TokensSavingsStatus
5021,35320,0736.0%
10035,65320,07343.7%
25078,55320,07374.4%
500150,05320,07386.6%
674LIMIT200,00020,07390.0%
795ACTUAL234,123*20,07391.4%
1,000293,053*20,07393.2%
5,0001,437,053*20,07398.6%
10,0002,867,053*20,07399.3%
*Exceeds 200K context window - CLAUDE.md cannot work
Both approaches work
Only Continuity works

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.

$36
Continuity monthly cost
(at 600 sessions/month)
$421
CLAUDE.md monthly cost
(at 795 decisions)
$4,623
Yearly savings
with Continuity

Mathematical Proof

Formal proof that Continuity provides asymptotically superior token efficiency

SymbolDefinitionMeasured Value
nTotal number of decisions795
dAverage tokens per decision286
bBase CLAUDE.md instructions7,053
qSearch queries per session3
rResults returned per query15
CContext window limit200,000

The Fundamental Equation

lim[n→∞]TContinuity / TCLAUDE.md = 0

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)

  1. Download the latest .vsix file
  2. Open VS Code
  3. Press Cmd/Ctrl+Shift+P
  4. Type "Extensions: Install from VSIX..."
  5. Select the downloaded file
  6. Reload VS Code when prompted
Note: VS Code Marketplace listing coming soon. Manual installation is currently the only method.

First Steps

After installation:

  • Run Continuity: Initialize in 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

Decision Logging

Manual capture of architectural decisions

MCP Integration

Core MCP resources available

~
5 Decisions Max

Limited to 5 decisions

~
30-Day History

Older decisions hidden

Pro Features

Upgrade to Pro
Auto-Log Modes

Smart, immediate, and review modes

Semantic Search

AI-powered context retrieval (O(1) efficiency)

Knowledge Graph

Interactive D3.js visualization

Unlimited Decisions

No storage limits - scale to 10,000+

AI Noise Filtering

4-layer intelligent filtering

Export

CSV, JSON, Markdown formats

License Management

Activation

After purchasing, you'll receive a license key via email. Activate it in VS Code:

  1. Press Cmd/Ctrl+Shift+P
  2. Type "Continuity: Activate License"
  3. Enter your license key and email
View detailed activation guide →

License Types

Monthly Subscription$15/month

Renews monthly, cancel anytime

Annual Subscription$139/year

Renews annually, save 23% vs monthly

Lifetime License$399 one-time

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_decision

Log architectural decisions with question, answer, and optional tags

@continuity search_decisions

Search logged decisions by keyword or semantic query - O(1) efficiency

@continuity session-handoff

Get 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/activate

Activate a new device for a license

DELETE /api/devices/:device_id

Deactivate 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.