semble

What it does

Returns the exact snippets an agent needs instead of making it read files, which the project measures at roughly 99% fewer tokens than grep-plus-read, with full-codebase indexing and search completing in under a second. Notably it runs entirely on CPU — no API keys, no GPU, no external service — and exposes an MCP server so agents can query it directly. The speed and reduction figures are the project's own benchmarks, so verify on your repository. MIT.

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

Screenshots & visuals

Before you start

• Setup difficultyEasy to start
• Command lineRequired
• API keyNot required
• Sends data onlineNo

Judged automatically from the project's own metadata. Always confirm on the official page.

semble FAQ

Is semble free?

Yes. It runs on your own machine, so there is no usage-based cost either.

Do I need to install anything or write code to use semble?

It connects to an MCP-capable AI app such as Claude. It does not run on its own.

Does semble work on a phone?

No. It needs a computer.

Can I use semble commercially?

The licence is MIT, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.

How it compares

The conditions that decide whether you can actually use it, side by side.

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.

Other mcp connectors tools