# Sensei

> Sensei — senseiissei-sensei. Use this tool when you need to securely and efficiently interact with AI models while minimizing data transmission. Sensei solves the problem of excessive token usage by compressing prompts, reducing the amount of data sent to AI services like Claude Code, Cursor, and OpenAI. It provides a drop-in gateway with a simple interface, accepting prompts as input and returning compressed outputs, making it ideal for use cases where data privacy and efficiency are crucial.

Canonical page: https://skillsregistry.net/skills/senseiissei-sensei  
JSON: https://api.skillsregistry.net/v1/skills/senseiissei-sensei

## Description

Self-hosted AI workspace that compresses prompts before they leave your machine — 79% fewer tokens, measured. Drop-in gateway for Claude Code, Cursor, Aider and any OpenAI/Anthropic client, plus an MCP server. Free, MIT, zero telemetry.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/SenseiIssei/Sensei)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "senseiissei-sensei"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/senseiissei-sensei` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/senseiissei-sensei/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt