EN | δΈ­ζ–‡

AI Coding Without Uploading Your Code

Run private coding assistants against an LLM and Git server you control. MTCode maps remote services to local ports so your tools work as if everything were running on your laptop.

⬇ Download Free
πŸ›‘ Privacy — End-to-end encrypted. No MTCode infrastructure in your data path.
⚑ Simplicity — No public IP, domain, VPN, or port forwarding.
πŸš€ Performance — Direct peer-to-peer data path, with no relay hop.

The Problem

AI coding assistants need access to code context. For closed-source projects, contractor work, security-sensitive codebases, or NDA-protected repositories, sending that context to hosted models may be unacceptable.

At the same time, self-hosted AI coding is becoming much more realistic. Open-weight coding models are improving quickly, and more capable local AI hardware is reaching developers, small teams, and offices β€” from high-VRAM gaming GPUs and workstations to unified-memory desktops and personal AI systems. For many daily coding tasks, a private model server is no longer just an experiment; it can be a practical development tool.

A common solution is to run a private LLM on a high-VRAM GPU at home or in the office, and to keep source code in a self-hosted Git server such as Gitea, Forgejo, or GitLab CE. But those services are tied to one location while your laptop moves between home, office, client sites, and travel.

Opening ports exposes services to the public internet. VPNs add network-level complexity. Tunnel services add a third-party relay. MTCode DirectLink lets you access selected private services from anywhere while keeping them off the public internet.

What MTCode Does

πŸ€–

Private LLM for coding agents

Register your Ollama, LM Studio, vLLM, or MTCode-LLM endpoint with MTCode Server. MTCode Portal maps it to a local address on your laptop, so compatible coding tools can connect as if the model were local.

πŸ”

Private Git from anywhere

Publish your self-hosted Git service through MTCode Server. Clone, pull, and push through a local Portal mapping without exposing the Git server publicly.

🎯

Service-level access

MTCode shares only the services you register β€” for example, an LLM endpoint and a Git web interface β€” not the entire computer or local network.

How It Works in This Scenario

  1. Install MTCode Server on the computer running your LLM server and/or private Git server.
  2. Register the service ports you want to access remotely, such as Ollama on port 11434 or the web port for Gitea.
  3. Install MTCode Portal on your laptop and sign in.
  4. MTCode Portal maps each authorized service to a local port on your laptop. You can double-click the port number to change it to the specific port your application expects, such as localhost:11434.
  5. Your coding agent or Git client connects to the local address, while the actual service continues running on your private computer.

Why This Matters

Getting Started

  1. Run your LLM or Git service on your private computer.
  2. Publish its port with MTCode Server.
  3. Connect from your laptop with MTCode Portal.