Hicortex — AI Fleet Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 636 installs a week from npm. Last commit 29 Oct 2026.
Shared fleet memory for AI agents: nightly self-correction, recall every prompt (supported agents).
We read the source, 4 d ago · rules 995398eba69f
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.
этот файл ставится пользователю, но в репозитории его нет
execFile(
/search /memory /update /delete /identity — the browser + agent rail
function nodeVal(n) {
import { existsSync, readFileSync, writeFileSync, mkdirSync, copyFileSync, readdirSync, statSync, symlinkSync, rmSync, renameSync } from "node:fs";
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 hicortex -- npx -y @gamaze/hicortex
{
"mcpServers": {
"hicortex": {
"command": "npx",
"args": [
"-y",
"@gamaze/hicortex"
]
}
}
}
[mcp_servers.hicortex]
command = "npx"
args = ["-y", "@gamaze/hicortex"]
{
"mcpServers": {
"hicortex": {
"command": "npx",
"args": [
"-y",
"@gamaze/hicortex"
]
}
}
}
{
"servers": {
"hicortex": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@gamaze/hicortex"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
HICORTEX_AUTH_TOKEN (Bearer token for a remote Hicortex server (server prints it via `hicortex status`). Optional — a local server needs no token), HICORTEX_SERVER_URL (URL of a remote Hicortex server (e.g. https://your-server:8787). Optional — omit for a local server on this machine).
On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
Persistent memory for AI agents - save once, recall in every session, project and tool.
Shared memory for AI agents, with a receipt for every write. Hosted MCP at agentics.you/mcp.
Self-correcting agent memory + MCP server: recall, supersede/revert/review corrections, erasure.
Context selection and compression for AI agents - recall measured, not claimed.
Private, encrypted memory about you, shared by all your AI agents. Self-hosted; runs on a Pi.
Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP.
StremAI MCP: shared memory for AI coding agents. Connected agents can recall. OAuth + local stdio.
Answers built from our own checks of this server.