Skip to content

NanoTeams 1.7.2 — Fixes & Improvements

Choose a tag to compare

View all tags
@jmstajim jmstajim released this 19 Jul 20:27
· 15 commits to main since this release
1.7.2
707cc33

A fix release. Sampling settings move to LM Studio, model loading becomes explicit.

🛠 Improved

  • LM Studio owns sampling — NanoTeams sends no sampling keys on the wire, so the per-model config in My Models is what runs. The Generation card in Settings → LLM, the Vision response limit, and the temperature / response-limit fields on per-role and team-generation overrides are removed.
  • Chat, Vision, and embeddings stay resident together — models are explicitly loaded before each request, which exempts them from LM Studio's single-JIT-instance limit and idle eviction.
  • Model switching — switching models unloads the previous one. The unload is skipped while a run is live, and a model another slot still points at is left loaded.

🐛 Fixed

  • Per-role LLM overrides dropped the global temperature.

System Requirements

  • macOS 15.0 or later
  • LM Studio 0.4.0 or later
  • Apple Silicon recommended for best local-LLM performance
  • macOS 26+ required for private voice dictation

Install

  1. Download NanoTeams.app.zip and extract it.
  2. Drag NanoTeams.app into /Applications.
  3. If macOS blocks the app on first launch: System Settings → Privacy & Security → Open Anyway.
  4. Launch LM Studio, load a recommended model, then launch NanoTeams.

Build from Source

git clone https://github.com/jmstajim/NanoTeams.git
cd NanoTeams
xcodebuild -project NanoTeams.xcodeproj -scheme NanoTeams -configuration Release build

Links

Topics: macOS · AI coding assistant · local LLM · LM Studio · multi-agent AI · AI agents · sampling · model loading · sandbox · open source · private AI · on-device · offline AI · Apple Silicon · Swift · SwiftUI · agentic chat · code generation

Assets 3
Loading