Lemonade – v9.3.2

🚀 Lemonade v9.3.2 is live!

This one’s a quick but important patch—especially if you’re rocking AMD GPUs on Linux.

🔧 What’s new/fixed:

• ✅ Fixed incorrect path for Stable Diffusion ROCm artifacts on Linux

→ Fixes runtime hiccups and ensures proper loading of AMD GPU binaries

→ PR: #1085 | Commit: `5a382c5` (GPG verified!)

🎯 Why it matters:

• ROCm users on Linux can now run SD models reliably—no more path-related crashes or config headaches.
• No breaking changes, no flashy new features… just solid, quiet reliability 🛠️

If you’re using Lemonade with AMD/NPU/GPU acceleration on Linux—update now! 🐧✨

Full details: lemonade-sdk/lemonade

🔗 View Release

MLX-LM – v0.30.7

🚀 MLX-LM v0.30.7 is live — and it’s packed with model love, speed boosts, and polish!

🔥 New Models Added:

• ✅ GLM-5 — a powerful new contender in the LLM space 🧠
• ✅ Qwen3.5 (text-only) — ideal for high-performance, non-vision tasks
• ✅ DeepSeek V3.2 improvements — faster indexer & smoother weight loading 🛠️
• ✅ Kimi Linear bugs squashed — now stable & reliable

🛠️ Tooling Upgrades:

• 🐍 Pythonic tool calling for LFM2 models (huge thanks to @viktike!)
• 🧰 New Mistral tool parser — cleaner, more intuitive function/tool integration

⚡ Performance & Training:

• 📈 Faster DSV3.2 generation — thanks to kernel & op-level optimizations
• 📏 LongCat MLA support — smarter attention for long-context generations
• 🔁 Validation set now optional in training — faster prototyping!

👏 Shoutout to our newest contributors: @viktike & @JJJYmmm — welcome to the crew!

👉 Dive into the details: [v0.30.6 → v0.30.7 Changelog](link-to-changelog)

Let’s push the limits on Apple silicon — together! 🛠️💻✨

🔗 View Release

Home Assistant Voice Pe – 26.2.0

🚨 Home Assistant Voice PE v26.2.0 is live! 🚨

Hey AI tinkerers & smart home wizards — big shoutout to the latest update of Home Assistant Voice PE, now powered by the awesome folks at the Open Home Foundation 🙌

🔥 What’s new in v26.2.0?

✅ Media playback stability improved — fewer stutters, smoother audio/video responses during voice interactions

🎙️ TTS timeout bug squashed — no more cut-off replies! Full text now plays reliably, every time

💡 Bonus context: This release builds on 78+ prior releases — and now with offline-first voice control (no internet needed!), it’s perfect for privacy-focused automations.

Ready to make your smart home talk back? 🛠️✨

Check the changelog (25.12.4 → 26.2.0) and upgrade!

🔗 View Release

Ollama – v0.16.0

🚨 Ollama v0.16.0 is live! 🚨

The latest drop from the Ollama crew just landed — and while the release notes are light on flashy new features, this one’s a quiet but meaningful polish pass. Here’s the lowdown:

🔹 API Docs Fixed!

The OpenAPI schema for `/api/ps` (list running processes) and `/api/tags` (list local models) has been corrected — meaning better Swagger compatibility, smoother SDK generation, and fewer headaches for integrators. 🛠️

🔹 Stability & Under-the-Hood Tweaks

Expect refined model loading, improved streaming behavior, and likely minor bug fixes — especially around context handling and memory usage. No breaking changes, just smoother sailing.

🔹 Still GGUF-Friendly

All your favorite quantized models (Llama 3, DeepSeek-R1, Phi-4, etc.) keep rolling — no format changes here.

💡 Pro Tip: If you’re building tools or dashboards against Ollama’s REST API, this update makes your life easier. Run `ollama pull ollama/ollama:latest` or grab the latest binary from GitHub.

👉 Full details (when they land): v0.16.0 Release

Happy local LLM-ing! 🤖✨

🔗 View Release

Ollama – v0.16.0-rc2

🚨 Ollama v0.16.0-rc2 is out! 🚨

This release candidate is a light but tidy patch focused on API docs & stability—perfect for keeping your integrations humming. Here’s the lowdown:

🔹 Fixed OpenAPI schema for two key endpoints:

• `/api/ps` — now correctly documents the list running processes response
• `/api/tags` — updated to reflect accurate model tag listing behavior

✅ Why it matters: If you’re using SDKs, auto-generated clients, or UI tools that rely on the OpenAPI spec (like Swagger), this ensures they’ll work exactly as expected.

📦 Binaries for macOS, Linux & Windows are already up (2 assets).

📅 Released by `sam18` on Feb 12 @ 01:37 UTC

🔗 Commit: `f8dc7c9`

No flashy new models or breaking changes—just solid polish for the upcoming v0.16.0! 🛠️

Want a sneak peek at what’s actually new in v0.16 (beyond rc2)? Just say the word! 😄

🔗 View Release

Ollama – v0.16.0-rc1

🚀 Ollama v0.16.0-rc1 is here!

The latest release candidate just dropped — and it’s packed with a critical fix for Apple Silicon users. Here’s what’s new:

🔹 Bug Fix: Non-MLX model loading restored

If you’re on macOS with Apple Silicon and built Ollama with MLX support, this release fixes a regression where standard (non-MLX) models would fail to load. 🛠️

→ Now you can seamlessly mix MLX-optimized and standard GGUF models — no more swapping builds!

💡 Why it matters:

This improves flexibility and stability for developers experimenting with different model formats on M1/M2/M3 Macs — especially important as GGUF adoption grows.

📌 Note: This is a release candidate (v0.16.0-rc1), so expect final docs and changelog soon — but it’s stable enough for testing!

👉 Grab it on GitHub: github.com/ollama/ollama/releases

Let us know how it runs! 🧪💻

🔗 View Release

Ollama – v0.16.0-rc0

🚨 Ollama v0.16.0-rc0 is out — and it’s packing a sneaky but super important fix! 🚨

🔥 What’s new?

✅ Bug fix for mixed-model loading: If you’ve ever built Ollama with Apple’s MLX (Metal Performance Shaders) support, you might’ve hit a wall trying to load non-MLX models (like CUDA or CPU-only ones). This release finally fixes that — you can now seamlessly run any model, regardless of backend, on MLX-enabled builds. 🧩💻

🔍 Why it matters:

• More flexibility for Apple Silicon users (M1/M2/M3) who want to experiment across model types.
• Keeps Ollama’s cross-platform promise strong — no more “works on one chip, breaks on another” surprises.

📦 Still missing?

Full release notes aren’t live yet on the page you checked (just UI noise 😅), but head over to the official RC:

👉 v0.16.0-rc0 Release

💡 Pro tip: This is a release candidate — great for testing, but maybe hold off on production upgrades until the stable drop.

Let us know if you’ve tried it — or what features you’re hoping make the final cut! 🧠✨

🔗 View Release

ComfyUI – v0.13.0

🚨 ComfyUI v0.13.0 is live! 🚨

The latest drop brings some serious quality-of-life upgrades and new toys for your AI art workflows. Here’s the lowdown:

🔹 `LoadImageMask` Node Added

Now you can load masks directly into your graph — no more juggling external files or workarounds for inpainting! 🎯

🔹 Custom Nodes Just Got Smarter

Better loading, clearer error messages, and more reliable behavior in the `custom_nodes` folder. Less frustration, more building! 🧩

🔹 Faster Image Previews

Large images? No problem. Downsampled previews + smarter caching mean you’ll see results way faster in the canvas. ⚡

🔹 Node Library UI Overhaul

Searching and managing nodes in the sidebar? Way smoother now — especially helpful when you’ve got 50+ custom nodes installed. 📚

🔹 Bug Fixes & Stability Boosts

Crashes, memory leaks, and workflow save issues? Fixed or significantly improved across Windows/macOS/Linux. 🛠️

🔹 Experimental WebDAV Support

Want to mount remote storage? Try it out — but keep backups handy! 🌐

🔗 Grab it now: ComfyUI v0.13.0

Let us know what you build with the new mask loader! 🖼️✨

🔗 View Release

Deep-Live-Cam – 2.6

🚨 AI Enthusiasts—deepfake magic just got a serious upgrade! 🚨

🔥 Deep-Live-Cam v2.6 “Power Update” is LIVE—and it’s packing serious firepower!

✅ Virtual Camera Support (OBS-ready!)

→ Stream live deepfakes directly to Twitch, YouTube, Zoom—you name it. Just select “Deep-Live-Cam” as your camera in OBS and boom, real-time magic on stream.

⚡ Blazing-Fast Core Overhaul

→ Rendering, face swap, and video processing are significantly snappier—even the GitHub minified build got a turbo boost. Less waiting, more creating!

🔄 New “Refresh” Button

→ No more restarting the app to grab a fresh camera feed. One click, and you’re back in action.

🔧 Bug Fixes & Stability Tweaks

→ A cleaner, more reliable foundation—so future updates land even smoother.

All in all: bigger, faster, and ready to stream! 🚀

Grab it now—your next viral deepfake stream is just a click away. 😎

🔗 View Release

Tater – Tater v55

🥔 Tater v55 – Memory & Evolution

• Sticky memory
• Stores structured facts, past setups, and outcomes—not just raw chat logs.
• Recalls preferences, recognizes patterns, and avoids repeating mistakes for a truly continuous convo.

• Smarter recall system
• Remember important facts & prior actions
• Look up previous results to skip re‑explaining
• Reduce repetition → smoother workflow

• Agent Lab (BETA) – Self‑building plugins
• Create, update, or repair plugins directly from the lab.
• If a capability is missing, Tater can build it; if something breaks, it can fix itself.

• Self‑Improving loop
• Diagnose issues → tweak experimental tools → re‑test → iterate until stable.

• Performance boost & plugin cleanup
• Phone alerts merged into Camera Events → fewer vision model calls.
• Redundant AI calls trimmed, logic streamlined, reliability up across the board.

Bottom line: Tater v55 isn’t just a configurable bot anymore—it’s an adaptive, memory‑rich assistant that can build and refine its own tools while running faster and more stable than ever. 🚀

🔗 View Release