Anyone here tried Nanobot or Nanoclaw with Local LLM backend?

<!-- SC_OFF --><div class="md"><p>I've been thinking about this as local models get better at </p> <p>tool use — shell access, file system, HTTP requests, MCP. </p> <p>If a prompt

<!-- SC_OFF --><div class="md"><p>Im looking to setup a local offline llm for a business i work for, just need it to run on our shared server and be able to do admin type stuff on

<!-- SC_OFF --><div class="md"><p>Been using ClaudeCode CLI with Opus 4.6 and many MCP's and honestly its addicting. </p> <p>Just tell it what to build and it does everything —

<!-- SC_OFF --><div class="md"><p>Has anyone figured out an actually robust browser agent powered by a local LLM? As a layperson I’ve tried using openclaw powered by local LLM,

<!-- SC_OFF --><div class="md"><p>With all this talk about Mythos being able to hack into. US government systems, I was wondering if anyone has tried to get root on their own

<!-- SC_OFF --><div class="md"><p>I have snobbishly long felt that the local models were not 'up to my standards' for local development, or otherwise able to compete with GHCP,

<!-- SC_OFF --><div class="md"><p>Tomorrow, I am getting delivery of a 13&quot; M5 macbook air with 32gb RAM and 1T SSD. Currently, I have pro subscriptions to Gemini, Perplexity

<!-- SC_OFF --><div class="md"><p>Anthropic opened Cowork for Bedrock/Vertex/Azure providers and also Custom Inference Endpoints.</p> <p>However, connecting it to a local proxy