Laika Orbit recall

io.github.Laika-Dynamics-LtdPublished by GitHub account Laika-Dynamics-Ltdv0.1.2Updated Oct 24, 2026

Zero-model recall over your docs: the section that answers a question, in about a millisecond.

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Lets an assistant answer questions from a local folder of Markdown and text files by returning the matching section and its source file, without calling a…

What you can do
Laika Orbit recall indexes a local corpus of Markdown and text and answers questions by returning the exact section that matches plus the file it came from. It exposes three tools: recall (answer a question with the matching section and its source), get (read a file) and status. Retrieval is a fixed pipeline of tokenising, inverted-index scoring, keeping the top five with a confidence margin, opening only the winner, slicing out the matching section, following at most one pointer, and packing the result. It also has a terminal CLI for indexing, recalling, linting router files and printing a packed prompt.
When to use it
Useful when an assistant works over a local documentation or notes folder and you want to replace grep-and-read-whole-files with a single low-token call. It is aimed at Claude Code users who keep a project corpus, especially with router files that point to where things are.
Requirements
Runs locally over stdio as an npm package (laikaorbit), so Node 22 or newer is needed. The corpus defaults to the working directory or the BRAIN_ROOT environment variable, and a --root directory can be given instead. Optional configuration lives in brain/index.config.json. Reading .docx, .rtf and .odt uses macOS textutil, and PDFs need pdftotext installed. No authentication is declared.
Before you install
It reads local files from the configured root, so point it only at folders you are comfortable exposing to the assistant. It makes no network calls and nothing leaves the machine. The get tool reads files, and indexing writes an index for the folder, so consider what a chosen root contains before adding the server.

Installation

In SourceWeft

  1. Open Laika Orbit recall in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Laika Orbit recall

Zero-model recall over your files. Ask a question, get back the exact section that answers it and the file it came from, in about a millisecond, without calling a model. Built for Claude Code: as an MCP server it replaces grep-and-read-whole-files with one call, using far fewer tokens.

The retrieval engine inside Laika Orbit, published on npm as laikaorbit.

Use it with Claude Code

bash
claude mcp add laikaorbit -- npx -y laikaorbit mcp

Claude Code starts the server in your project folder and gets three tools: recall (answer a question with the matching section and its source), get (read a file) and status. To point it at another folder, add --root <dir> after mcp.

Use it from the terminal

bash
npx laikaorbit index                          # build the index for this foldernpx laikaorbit recall "how do we roll back a deploy"npx laikaorbit lint                           # check router files for dangling pointersnpx laikaorbit ask "…"                        # print the packed prompt for a model

Every command takes --root <dir>; otherwise the corpus is BRAIN_ROOT, then the working directory.

How it finds the answer

Seven steps, none of them a model call: tokenise the question on word boundaries, score it against an inverted index, keep the top five with a confidence margin, open only the winner, slice out the matching ## section, follow at most one pointer, and pack the result.

It works on any folder of Markdown and text. It works best with router files: short typed pointer lists in brain/routers/*.md that say where things are, written the way questions are asked:

markdown
## 1 — deploys
- Files: notes/deploy.md — how production deploys are rolled back- Rules: notes/freeze.md — no deploys on Fridays after 2pm

Which folders are indexed, and how, is set in brain/index.config.json (optional). .docx, .rtf and .odt are read with macOS textutil, and PDFs with pdftotext when it's installed.

Requirements

Node 22 or newer. Nothing leaves your machine: it reads local files and makes no network calls.

Licence

MIT © Laika Dynamics Limited

Source: packages/laikaorbit/README.md at commit b4a109c

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.2LatestSep 19, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts