lynxai-team/goinfer

Local LLM proxy, DevOps friendly

44
/ 100
Emerging

This tool helps DevOps teams securely expose locally-hosted Large Language Models (LLMs) to external users or applications without complex network configurations like VPNs or port forwarding. It takes your GGUF-formatted LLM files running on a local GPU machine and provides a secure, encrypted HTTPS API endpoint that can be accessed from anywhere. This is ideal for organizations or individuals who want to leverage their powerful local GPUs for LLM inference while maintaining data privacy and simplified access.

Use this if you need to provide secure, remote access to your organization's or personal GPU-accelerated LLMs without exposing your internal network or relying on public cloud inference services.

Not ideal if you don't have local GPUs, don't need remote access to your LLMs, or are comfortable with existing, simpler solutions like direct local network access.

DevOps LLM-deployment GPU-inference network-security remote-access
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Go

License

MIT

Category

llm-api-gateways

Last pushed

Feb 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/lynxai-team/goinfer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.