← back to the directory
Application Inference & Serving

LocalAI

1A 2self-hosted, 3OpenAI-compatible 4local 5AI 6API.

the six Ws · specification

W1 Who

Open-source project by Ettore Di Giacinto.

W2 What

Serves local models behind an OpenAI-compatible API.

W3 Where

Runs on your own CPU or GPU hardware.

W4 When

When replacing OpenAI with local models.

W5 Why

Drop-in local alternative to hosted APIs.

W6 With

Local model files and a machine.

GoInferenceSelf-hosted

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.