Continuity - Synthetic Memory for AI Coding Assistants Logo
Continuityby Hackerware
Start
Mathematically Proven

95.7% Token Savings
Verified & Reproducible

Current benchmark with 1,650 decisions proves Continuity is 23.3× more efficient than CLAUDE.md. See the math, run the tests yourself.

95.7%+
Token Savings
23.3×
More Efficient
O(1)
Complexity
968
Decision Breakpoint

Quick Navigation

Token ComparisonGrowth CurveCalculatorCLAUDE.md vs ContinuityMathematical ProofGetting Started

Token Comparison

CLAUDE.md: 336,704 tokens. Continuity: 14,472.

1,650
Decisions
336,704
CLAUDE.md tokens
14,472
Continuity tokens
95.7%
Savings

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.

0K50K100K150K200K250K300K350K025050075010001650Number 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 about 968 decisions and becomes unusable.

At 1,650 decisions CLAUDE.md would require 336,704 tokens - about 168.4% of the context window. Continuity stays at 14,472 tokens for the current benchmark.

Calculate Your Savings

See how much you'll save based on your project size

Calculate Your Savings

100
10 requests500 requests
Monthly Savings
$96.67
vs current benchmark baseline
Annual Savings
$1160.04
First year total
Net Monthly
$+87.67
After $9 subscription
Return on Investment
+974%
✅ Profitable from day one
Token Savings
95.7%
Verified against the current benchmark snapshot
Benchmark cost without Continuity:$101.01/month
Benchmark cost with Continuity:$13.34/month
Your Total Savings:$96.67/month
Verified against current benchmark data (1,650 decisions)
See full methodology →•Run test yourself

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 around 968 decisions

•No search capability

Best for: Project instructions, coding standards, static context (~5,277 base 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 (14,472 tokens at the current benchmark)

FeatureCLAUDE.mdContinuity
Static project instructions
Store 100 decisions
Store 500 decisions
Store 968+ 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 1,650 decisions (336,704 tokens — 168.4% of the 200K context window)
  2. 2.Claude scans through everything manually
  3. 3.You've already used 168.4% of context before even asking
  4. 4.Doesn't work - exceeds the context limit
With Continuity
  1. 1.Claude calls search_decisions("authentication")
  2. 2.Returns only the relevant decisions (~14,472 tokens at the benchmark)
  3. 3.You've used just 7.8% of context
  4. 4.Works with 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
5015,32014,4725.5%
10025,36314,47242.9%
25055,49314,47273.9%
500105,70914,47286.3%
968LIMIT199,71414,47292.8%
1,000206,142*14,47293.0%
1,650ACTUAL336,704*14,47295.7%
5,0001,009,601*14,47298.6%
10,0002,013,925*14,47299.3%
*At about 968 decisions, CLAUDE.md hits the 200K context limit
Both approaches still work below the limit
Above the limit, only Continuity remains usable

Key Insight: Savings increase as your project grows.

The more decisions you log, the more efficient Continuity becomes. At 10,000 decisions, you save nearly 99.4% of tokens.

Monthly Cost Comparison

$26.05
Continuity monthly cost
(current benchmark)
$606.07
CLAUDE.md monthly cost
(current benchmark)
$580.02
Monthly savings
at the benchmark scale

Mathematical Proof

Formal proof that Continuity provides asymptotically superior token efficiency

SymbolDefinitionMeasured Value
nTotal number of decisions1,650
DTotal decision tokens331,427
dAverage tokens per decision200.9
bBase CLAUDE.md instructions5,277
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?

A RAG-based synthetic memory system for AI coding assistants. Captures decisions, tracks changes, and provides persistent context.

O(1) Token Efficiency

Semantic search retrieves only relevant decisions — constant token usage regardless of project size.

Installation

  1. Open VS Code Marketplace
  2. Click Install
  3. Reload VS Code

First Launch

  • Zero-click setup — auto-detects AI tools
  • Initial scan — creates draft decisions from codebase
  • Git seeding — pre-populates from commit history
  • Creates .continuity/ folder with plain JSON

14-Day Free Trial

Full Pro access, no credit card required. After trial, unlimited logging stays free.

Features

Trial + Free Tier

✓
All Pro Features for 14 Days

Unlimited decisions, semantic search, knowledge graph

✓
Zero-Click Setup

Auto-detects and configures AI tools

✓
5 Detection Layers

19 detection points auto-capture decisions

Pro Features

Upgrade
★
Semantic Search

O(1) efficiency

★
Knowledge Graph

1,500 nodes

★
Dream Engine

4-phase consolidation

★
Decision Lifecycle

Auto-outdating

★
Code Intelligence

Refactoring safety

★
Unlimited Decisions

No storage limits

License Management

Activation

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

License Types

Monthly$9/month

Cancel anytime, 14-day free trial

Annual$89/year

Save 18%, 14-day free trial

Lifetime$199 one-time

Never expires, all future updates

MCP Integration

What is MCP?

Continuity uses the Model Context Protocol to provide AI assistants with persistent memory and decision logging.

Memory Tools

log_decision

Log decisions with question, answer, and tags

search_decisions

Search by keyword or semantic query — O(1)

get_quick_context

Load project history at conversation start

session-handoff

Complete project context for handoffs

API Reference

POST /api/licenses/validate

Validate a license key with device info

POST /api/devices/activate

Activate a new device

DELETE /api/devices/:device_id

Deactivate a device

Troubleshooting

License activation fails

  • Verify license key (check for typos)
  • Use the email from your purchase
  • Check internet connection

MCP not working

  • Verify Continuity is installed and activated
  • Check MCP server logs in VS Code Output
  • Restart your AI assistant

FAQ

Why is Continuity more efficient than CLAUDE.md?

CLAUDE.md loads ALL decisions (O(n)). Continuity retrieves only relevant ones (O(1)). At 1,650 decisions: 95.7% savings.

What happens past 968 decisions?

CLAUDE.md exceeds the 200K context window. Continuity keeps working.

How much money will I save?

$580.02/month or $6960.21/year in benchmark-model savings.

Is my data secure?

All decisions stored locally in .continuity/ — never on our servers.

What AI assistants work?

Claude Code, Cursor, GitHub Copilot, Google Gemini, and more via zero-click setup.

Still have questions?

Our team is here to help.

Email SupportActivation Guide