v0.38.3

Mesh-LLM/mesh-llmv0.38.3Mar 22, 2026by michaelneale

AI Summary

Implemented an expandable thinking stream to visualize reasoning tokens and auto-routing load spreading to handle concurrent requests more effectively across models.

Key Highlights

Expandable thinking stream for live reasoning tokens
Auto routing load spread for concurrent requests
Updated project description

New Features

Expandable thinking stream
Auto routing load spread

Full Release Notes

## What's new

- **Expandable thinking stream**: while a model is thinking, click to expand and watch reasoning tokens stream in live (previously just showed a static spinner)
- **Auto routing load spread**: concurrent chat requests in auto mode now spread across top-scoring models instead of always queueing on the same one
- Updated project description and chat placeholder

### Install (macOS Apple Silicon)

```bash
curl -fsSL https://github.com/michaelneale/decentralized-inference/releases/latest/download/mesh-llm-aarch64-apple-darwin.tar.gz | tar xz && sudo mv mesh-bundle/* /usr/local/bin/
```