Ki! Ki! Beta
Download →

Your AI prompts shouldn't leak your data.

Ki! sits between you and any LLM. Names, emails, account numbers, health data — scrubbed locally in under 20 ms before the prompt is sent. Originals restored in the response. Works with Claude, GPT, Ollama, and inside Cursor, Windsurf, and Claude Code via MCP.

In beta — trying it out? We'd love to hear from you at beta@getki.ai

<20ms
Local scrub latency
0 bytes
PII sent to cloud
Ed25519
Tamper-proof audit trail
MCP
Works in your AI tools

See it in action

PII masked. Originals restored.

Ki! desktop — chat window showing PII masking in action
Names replaced with [PERSON_0] Emails → [EMAIL_0] Originals restored in the reply

Privacy layer for any LLM

Claude, GPT-4, Ollama, Gemini — Ki! intercepts the prompt, scrubs sensitive data, and unmasks the reply. Change nothing in your workflow.

Works inside your AI IDE

Ki! ships as an MCP server. Cursor, Windsurf, Claude Code, and VS Code can call Ki! directly — every snippet you share is scrubbed before it reaches the model.

100% local, fully offline

The scrubbing engine runs entirely on your machine. No telemetry, no cloud dependency. Your API key lives in your OS keychain — never on disk.

MCP — Model Context Protocol

Privacy inside the tools you already use

Add Ki! as an MCP server and every code snippet, document, or prompt you share with the AI is automatically scrubbed before it reaches the model.

Claude Code
Anthropic CLI
Cursor
AI code editor
Windsurf
Codeium
VS Code
Any MCP extension
// cursor / claude-code / windsurf — one line to add Ki!
"ki-mcp": { "command": "ki-mcp" }

The pipeline

Three steps. Invisible to you.

  1. 01
    You type normally
    Write your prompt as you always would — client names, account numbers, medical history. Ki! watches.
  2. 02
    Ki! scrubs before send
    Custom rules → allowlist → local AI NER. Three passes in under 20 ms. The LLM receives [PERSON_0], [EMAIL_0] — never the real data.
  3. 03
    Response restored
    Ki! reads the reply and swaps tokens back. You see the full, correct response. The LLM never touched the originals.
Ki! mascot

Try it. Tell us what breaks.

Ki! is in beta. Download it free, use it with any LLM, and share your feedback. Every bug report and honest opinion helps.