AI infrastructure dominates, four of seven releases
AI infrastructure claimed four of seven releases today. Ollama 0.33.0 integrated Claude Desktop model switching from the menu bar. llm CLI 0.33 moved to the OpenAI Python library 3.x and swapped httpx for httpx2. Qwen Code 0.22.0 addressed out-of-memory crashes in its web shell by bounding transcript retention. llama.cpp b10588 shipped a clang LTO fix. Nostr contributed Amethyst 1.14.0 with NIP-84 highlights support. Bitcoin posted Ashigaru Desktop 1.4.1. Self-hosting delivered Uptime Kuma 2.5.3 fixing a version-number regression.
Bitcoin
Nostr
- Amethyst 1.14.0. Adds NIP-84 highlights: composer, feed, and share intent support.
Self-hosting
- Uptime Kuma 2.5.3. Fixes a release-version-number regression.
AI
- Ollama 0.33.0. Claude Desktop integration: toggle individual Ollama models on and off from the menu bar, choose models directly within Claude.
- Qwen Code 0.22.0. Web shell now bounds transcript retention and trims oversized replays to prevent out-of-memory crashes.
- llm CLI 0.33. Migrates to OpenAI Python library 3.x, switches HTTP client from httpx to httpx2.
- llama.cpp b10588. Fixes clang LTO build issue.
Read on Freedom.Tech: https://freedom.tech/posts/2026-08-23-bitcoin-daily-brief/
Get the weekly recap in your inbox: https://freedom.tech/subscribe/
Freedom.Tech is powered by Foundation.
Catch the weekly discussion on Freedom Tech Friday via Ungovernable Misfits.
Write a comment