Together with toolnexus

toolnexus gives any LLM tools. browser-llm-nexus gives you the LLM.

Siblings, not layers — neither depends on the other. What they share is the tool schema.

	toolnexus	browser-llm-nexus
Runs	on your server	in the browser tab
Brings	tools (MCP, skills, HTTP, A2A)	the model (WebGPU / WASM)
Needs a model endpoint	yes	no — the weights are local
Data leaves the machine	to your model provider	never

The same tool, both sides

The authoring APIs differ, but both compile to the identical OpenAI function envelope — so a tool you designed for one is the same tool in the other.

// toolnexus — server side
defineTool({
  name: 'get_weather',
  description: 'Get current weather for a city',
  inputSchema: { type: 'object', properties: { city: { type: 'string' } }, required: ['city'] },
  run: ({ city }) => fetchWeather(city),
})

// browser-llm-nexus — in the tab
chat.tool('get_weather', 'Get current weather for a city',
  { city: 'string' },
  ({ city }) => fetchWeather(city));

Reach for browser-llm-nexus when the data must not leave the machine; reach for toolnexus when a model endpoint is fine and the hard part is the tools.

toolnexus docs →