Core concepts
Understanding these four concepts will make everything else in the docs click.Memory
A memory is a discrete, structured piece of context derived from your AI conversations. Not a raw transcript — a classified, ranked unit of information.The vault
Your vault is the encrypted store where memories live. You control it — locally with SQLite today, optionally synced to the 4StaX cloud when that ships. Every read and write to the vault is logged in an immutable consent ledger. You can always see what was accessed, when, and by which application.Relevance ranking
When your AI client needs context, kontxt doesn’t dump your entire memory archive into the prompt. It ranks candidates using four signals:| Signal | What it measures |
|---|---|
| Semantic similarity | How closely the memory matches the current task |
| Recency | How recently the memory was created or accessed |
| Access frequency | How often this memory has been useful before |
| Explicit importance | The importance score set when the memory was stored |
Memory types
| Type | Examples |
|---|---|
preference | Language choices, formatting preferences, communication style |
fact | Your name, role, project names, tech stack |
decision | Architectural decisions, tradeoffs made |
summary | Condensed session summaries |
instruction | Standing instructions for how AI should behave |
MCP — how it connects
MCP (Model Context Protocol) is the standard that lets AI clients talk to external tools and data sources. kontxt implements an MCP server that exposes your vault to any compatible client. When you ask Cursor or Claude Desktop something, the MCP client calls kontxt’s tools, retrieves relevant memories, and injects them into your prompt automatically. You don’t see it happening — it just works.Open source vs cloud
| kontxt (OSS) | 4StaX cloud | |
|---|---|---|
| Storage | Local SQLite | Hosted, encrypted |
| Sync | Single machine | Cross-device |
| Access | No account needed | Account required |
| Status | Available now | Waitlist |

