molla

tamnd/molla

★ 0 stars Mojo AI/LLM Updated 5d ago

Local inference server in pure Mojo. Speaks OpenAI, Anthropic, and MCP. Models are OCI artifacts. Same source runs on CPU, NVIDIA, AMD, and Apple GPUs. Apache-2.0 all the way down.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "molla": {
      "command": "npx",
      "args": [
        "-y",
        "tamnd/molla"
      ]
    }
  }
}

README Excerpt

A local inference server written in pure Mojo. It speaks OpenAI, Anthropic, and MCP, so anything that already talks to those APIs works against it by changing one environment variable. > **Status: early. Nothing works yet.** This repo currently holds the design, the build scaffolding, and the milestone plan. The first milestone (M0) is a spike to check that the whole idea is viable in Mojo at all. If it fails we will say so here and change course.

Topics

aianthropic-apicudaedge-aiggufgpuinferenceinference-serverllmllm-servinglocal-llmmachine-learningmcpmetalmodel-context-protocol

molla

Quick Install

README Excerpt

Topics

Related AI/LLM Servers