Laika Orbit recall runs on your own machine — the client starts it, so there is no endpoint to ping. 487 installs a week from npm. Last commit 21 Sep 2026.
Zero-model recall over your docs: the section that answers a question, in about a millisecond.
We read the source, 10 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const DELETE = /\brm\s+(?:-\w*[rf]\w*\s+)+|\bgit\s+branch\s+-[dD]\b|\bgh\s+(?:repo|release)\s+delete\b|\bdropdb\b|\bDROP\s+(?:TABLE|DATABASE|SCHEMA)\b|\baws\s+s3\s+rm\b|\bfind\b[^&|;]*-delete\b/i
const p = spawn(realBlender(), args, { stdio: 'inherit' })
join(KEY_DIR, 'id_ed25519'),
for (const id of ['lg-cpu', 'lg-mem']) $(id).innerHTML = GROUPS.map(([, l, c]) => `<span style="--c:${c}">${l}</span>`).join('')
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add laikaorbit -- npx -y laikaorbit
{
"mcpServers": {
"laikaorbit": {
"args": [
"-y",
"laikaorbit"
],
"command": "npx"
}
}
}
[mcp_servers.laikaorbit]
command = "npx"
args = ["-y", "laikaorbit"]
{
"mcpServers": {
"laikaorbit": {
"args": [
"-y",
"laikaorbit"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"laikaorbit": {
"args": [
"-y",
"laikaorbit"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
BRAIN_ROOT (The folder to recall from (default: the working directory)).
The author declared them in the registry entry; get the values from the project itself.
Answer questions from documents too large to fit in context, reading only the sections you need.
The most in-depth, source-backed context about a person for deep personalization and research.
The most in-depth, source-backed context about a person for deep personalization and research.
Security reviews, threat models over a repo or website, and remediation tracking, in your editor.
Convert a document once, then get back only the passages that answer a question.
Multiple AIs peer-review and debate your question, then return one fact-checked answer.
Query a verified document collection: passages that answer a question, with their source.
Query a verified document collection: passages that answer a question, with their source.
Answers built from our own checks of this server.