Continuity Ultimate
Memory that belongs to your code — not your model.
The Problem
You have explained your architecture to Claude four times this week. Copilot just suggested the exact pattern you rejected last month — and you spent twenty minutes remembering why. Your AI assistant burns tokens rediscovering context, contradicts past decisions, and leaves no trail when things break.
This is not a model problem.
It is a memory problem.
AI assistants forget everything when the session ends. Architectural decisions, constraints, and context vanish. You are not just losing productivity — you are losing control.
The Solution
Continuity creates synthetic memory — a persistent, local-first AI context layer that remembers architectural decisions and feeds them back to Claude, Cursor, or Cline automatically.
Stop re-explaining your codebase.
Start building.
Why This Is Different
Decisions are stored in your repo — not in chat history, not in vendor-managed memory. Your .continuity/ folder travels with your code.
Works with your AI tools today — native MCP integration lets Claude Code, Cursor, and Cline read and write decisions without copy-paste.
Core Capabilities
Persistent Decision Memory — Log architectural decisions once; AI recalls the why across sessions
Code-Linked Context — Bind decisions directly to code locations so AI understands changes in context
Seamless AI Handoff — Auto-generate session context with delta tracking for any MCP-compatible tool
Synthetic Memory Control — Own institutional knowledge locally with zero telemetry and full portability
Continuous Context Sync — Surface decision debt as architecture evolves
What Is Synthetic Memory?
AI sessions are stateless by default. Context evaporates when the tab closes. Some vendors offer "memory," but that state lives outside your control with unclear retention and no auditability.
Synthetic memory inverts this model.
Continuity persists architectural decisions as structured, versioned state inside your repo. You control retention, audit changes over time, and delete state without vendor coordination.
This is owned state for your codebase — not convenience memory for a model.
Privacy & Ownership
100% local. Zero telemetry. Your decisions never leave your machine unless you commit them yourself.
- No cloud dependencies
- No vendor lock-in
- Full git integration
Free vs Pro
Start free with 10 decisions. Verify your email for 5 more. Upgrade for unlimited.
|
Free |
Pro |
| Decisions |
10 (15 w/ email) |
Unlimited |
| MCP Integration |
✓ |
✓ |
| Semantic Search |
✓ |
✓ |
| Code Intelligence |
— |
✓ |
| Team Features |
— |
✓ |
Upgrade to Pro →
Get Started
- Install from the VS Code Marketplace
- Setup → Command Palette →
Continuity: Setup MCP
- Log decisions — your AI remembers the rest
Works With
- Claude Code
- Cursor
- Cline
- GitHub Copilot
- Any MCP-compatible AI tool
What's New in v2.3
Fluent AI Memory (Major Feature)
AI assistants now load context automatically — no manual setup required.
- Auto-Generated Instruction Files — CLAUDE.md, .cursorrules, and copilot-instructions.md are created/updated on startup with your project's decision history
- First-Call Context Injection — The first MCP tool response includes a context banner with recent decisions, session goals, and known topics
- Pattern-Based Reminders — When you add dependencies, change configs, or make architectural choices, Continuity prompts you to log decisions inline
- MANDATORY FIRST ACTION — Instruction files tell AI to call
get_quick_context immediately, ensuring memory loads before any suggestions
Semantic Search Improvements
- Fixed Cosine Similarity — Search scores now differentiate meaningfully (80% for exact matches vs 45-56% for loosely related)
- Full Embedding Coverage — All 800+ decisions now have MiniLM embeddings for true semantic search
Build & Packaging
- Reduced VSIX Size — Optimized from 55 MB to 45 MB
- Fixed MCP Extension ID — Supports both
hackerware.continuity (Marketplace) and hackerware.continuity-ultimate (Dev)
Previous (v2.2.11)
- MCP Tool Profiles — Core (12), Standard (29), or Full (92) tools
- Hybrid Search — Keyword + semantic matching by default
- CLI Limit Enforcement — Free tier limits across all interfaces
Documentation
Support
Memory that belongs to your code — not your model.
