Mebular

mcp
Guvenlik Denetimi
Basarisiz
Health Uyari
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Basarisiz
  • rm -rf — Recursive force deletion command in .github/workflows/ci.yml
  • exec() — Shell command execution in .github/workflows/publish.yml
  • rm -rf — Recursive force deletion command in .github/workflows/publish.yml
  • process.env — Environment variable access in .github/workflows/publish.yml
  • fs module — File system access in .github/workflows/publish.yml
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

One shared graph for every AI assistant and device — memory and tasks, local-first, signed, auditable, direct P2P sync. MCP tools; no hosted account.

README.md
Mebular

One memory. Every assistant. Every device.

A distributed memory network for your AI assistants.

Memory and tasks stay on your devices; devices sync directly.

CI License: MIT Node.js >=20 MCP

Start in 5 minutes · How it works · Website · 中文

No hosted account · No central coordinator


Star map baseline: the device network before hovering Task lanes and a fleet event: blue can send, gold can receive, gray unreachable

The map at rest: devices and their shared-subscription edges. · On hover: task-domain lanes plus live fleet traffic.
Blue and gold show this device's two-way task-domain reachability, not peer-to-peer links.

One memory

Why Mebular: one shared graph instead of a silo; local-first, direct sync, auditable, MCP

Get started

Desktop app setup: 1 Start deployment, 2 Create or join a Cloud, 3 Invite the next device

Other ways to start: Browser, CLI and Agent, all sharing one graph

Desktop app (v0.1.0, unsigned). Download from GitHub Releases: macOS Universal DMG, Windows x64 NSIS, Linux x64 AppImage and deb. Verify every file against SHA256SUMS.txt first. macOS needs right-click → Open (or Privacy & Security → Open Anyway); Windows SmartScreen needs More info → Run anyway. The app bundles Electron and its runtime, so it needs no local Node.js.

Or install the CLI and server:

npm install -g @mebular/core
mebular serve                                  # browser console
fleet quickstart --daemon                      # CLI start
mebular print-config --client opencode         # MCP config

How it works

Mebular network overview: each machine runs one node; nodes sync memory and tasks directly; add devices with a QR code or token

Write with memory_write, hand off with task_submit — the same graph, from any assistant.

Pairing flow: device A invites, device B joins with the QR code or token, then connection and the default grant happen automatically

Docs

Start Learn Run Trust
Quickstart
Install & pair
Architecture
Nodes & sync
Console
Local GUI
Limitations
Sensitive data
Agent skills
Setup playbooks
Fleet ops
Multi-machine
Release SOP
Release steps
Sealing docs
Protocol rules
Changelog
Release notes
Contributing
Quality gates
Security
Report a vuln
Website
Product site

Use with DSH
Keep the Mebular app running, then install the plugin from npm into DSH's web profile:
dsh plugin --profile web add @mebular/[email protected]
A Mebular sidebar panel embeds the same Console through ?embed=dsh (loopback only), and the official MCP client reaches the same graph. The plugin discovers the daemon by daemonUrl > MEBULAR_HTTP_PORT > runtime.json > 7331, so custom ports follow automatically. It has its own version line and is not part of the five-package lockstep. For plugin development, install from packages/dsh-plugin instead.
DSH plugin guide → · Integration notes →

Who does what
Who Handles
You One-time pairing, Cloud choice, invites, subscriptions.
Your assistant Memory reads and writes, task claim and completion.
Mebular Discovery, direct / relay / hole-punch, retries, certificates, service autostart.
Use it from code
import { Mebular } from 'mebular';

const mebular = new Mebular({
  storagePath: './store.jsonl',
  deviceId: 'device-a',
  network: { enabled: false },
});

await mebular.initialize();

Runnable examples: examples/quickstart writes and recalls a preference; examples/two-devices demonstrates offline sync.

v0.1.0 · early · MIT

Yorumlar (0)

Sonuc bulunamadi