v0.38.4

Mesh-LLM/mesh-llmv0.38.4Mar 22, 2026by michaelneale

AI Summary

Introduced an expandable thinking stream to visualize reasoning tokens in real-time and implemented auto-routing load spreading to distribute concurrent requests across top-scoring models.

Key Highlights

Expandable thinking stream for live reasoning tokens
Auto routing load spread across top-scoring models
CDN-ready cache headers for static assets
Updated project description and chat placeholder

New Features

Expandable thinking stream
Auto routing load spread
CDN cache headers

Full Release Notes

## What's new

- **Expandable thinking stream**: click to expand and watch reasoning tokens stream in live while model is thinking
- **Auto routing load spread**: concurrent chat requests spread across top-scoring models instead of queueing on one
- **CDN-ready cache headers**: hashed static assets served with immutable cache headers, SSE unbuffered for Cloudflare/CDN compatibility
- 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/
```