Browse
→ AI & Models
→ Gemm / Basalt MCP
Gemm / Basalt MCP
Local Apple Silicon LLM inference server with MCP stdio, REST, and WebSocket transports sharing one Swift actor over MLX on Metal. It runs Gemma, Qwen, and other MLX-compatible models fully on-device for IDE integration and local agent workflows, with no cloud calls or authentication. Public GitHub repository created September 2, 2026.
MCP unverified
Integration
| Transport | stdio |
| Auth | none |
| Endpoint | gemm mcp |
| Install | git clone https://github.com/goodmai/basalt.git && cd basalt && swift build |
Use Cases
| 01 | Run local on-device LLM inference from MCP-compatible IDEs on Apple Silicon |
| 02 | Share one model actor between MCP stdio, REST, and WebSocket clients |
| 03 | Prototype private agent workflows without sending prompts or model calls to a hosted service |
Tags
local-llm apple-silicon mlx metal gemma qwen swift on-device
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>