Keva
Context engineering for AI agents

A private knowledge vault for your AI coding agents

Keva gives your AI assistants structured, layered, long-term memory of your project — decisions, constraints and knowledge — so they stop forgetting.

Who we are

We are builders who got tired of re-explaining the same context to AI assistants every session. Keva is the memory layer we wished existed: structured, isolated per project, and fully under your control.

What we do

Keva stores your project knowledge in five cognitive layers and serves it back to any MCP-compatible AI client (VS Code Copilot, Claude Code, Gemini) exactly when it is needed.

Why Keva

Layered memory

Mission, project state, decisions, knowledge base and episodic history — weighted by intent.

Private by design

Each project is fully isolated. Only you can see your data. No cross-tenant bleed.

Connect any agent

A single connection token links VS Code, Claude Code or Gemini to your vault via MCP.

Local & zero-cost embeddings

Runs on local embeddings — no API keys, no per-token billing for memory.

Simple pricing

Free

€0

1 project. Everything you need to get started.

Start free

Custom

Let's talk

More projects, more space, personalized service.

Contact us

Give your agents a memory

Create your free account in seconds.

Start free