OpenSourcePulse

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9548 📅 Released: 2026-06-07 12:10 UTC 📊 Assets: 21 files 📝 What's New: <details open> spec : fix vocab compatibility check (#24256) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9547 📅 Released: 2026-06-07 09:38 UTC 📊 Assets: 21 files 📝 What's New: <details open> arg: Skip mmproj download when user supplied mmproj (#24239) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 android 🏷 Category: Community Suggested 🔖 Version: 5.0.0 📅 Released: 2026-06-07 06:16 UTC 📊 Assets: 6 files 📝 What's New: What's new: - Improved tunnel reliability and leak protection with new deferred endpoint bootstrapping - Improved tunnel status monitoring with real time handshake status monitoring - Kernel mode and ping monitoring removed - Full config and live tunnel view in quick format - Automatic ipv4/ipv6 endpoint fallback and recovery - Added support got DoT and custom endpoints for peer resolution DNS ... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 claude-code 🏷 Category: Community Suggested 🔖 Version: v2.1.168 📅 Released: 2026-06-06 23:41 UTC 📊 Assets: 10 files 📝 What's New: ## What's changed - Bug fixes and reliability improvements 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9544 📅 Released: 2026-06-06 21:20 UTC 📊 Assets: 21 files 📝 What's New: <details open> common/chat : fix LFM2/LFM2.5 reasoning round-trip and <think> leak (#24234) common/chat : fix LFM2 reasoning round-trip and stray <think> leak Gate by reasoning format and whether the template supports <think> </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9543 📅 Released: 2026-06-06 19:48 UTC 📊 Assets: 21 files 📝 What's New: <details open> mtmd: support "frame merge" for qwen-vl-based models (#21858) feat: add video support for Qwen3.5 various clean up revise the design fix llava-uhd case nits nits 2 --------- Co-authored-by: andrewmd5 <1297077+andrewmd5@users.noreply.github.com> </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 Exclave 🏷 Category: Community Suggested 🔖 Version: 0.17.44 📅 Released: 2026-06-06 10:07 UTC 📊 Assets: 4 files 📝 What's New: - Fix uTLS incorrectly applied to TrustTunnel HTTP/3 mode. 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9542 📅 Released: 2026-06-06 10:47 UTC 📊 Assets: 21 files 📝 What's New: <details open> completion : remove useless statics (#24226) Signed-off-by: Adrien Gallouët <angt@huggingface.co> </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel ... 🔗 [View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9538 📅 Released: 2026-06-06 04:56 UTC 📊 Assets: 21 files 📝 What's New: <details open> model : rename local nlayerall variable (#24209) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9537 📅 Released: 2026-06-06 04:34 UTC 📊 Assets: 21 files 📝 What's New: <details open> context : fix off-by-one comparisons to ngpulayers (#24208) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 claude-code 🏷 Category: Community Suggested 🔖 Version: v2.1.167 📅 Released: 2026-06-06 01:33 UTC 📊 Assets: 10 files 📝 What's New: ## What's changed - Bug fixes and reliability improvements 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 Ollama 🏷 Category: AI 🔖 Version: v0.30.6 📅 Released: 2026-06-05 20:00 UTC 📊 Assets: 17 files 📝 What's New: ## What's Changed `ollama launch omp` now integrates with [Oh My Pi](https://omp.sh), an AI coding agent with IDE integration MLX embedding layers now use NVFP4 global scale for improved quantization on Apple Silicon Full Changelog: https://github.com/ollama/ollama/compare/v0.30.5...v0.30.6 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9536 📅 Released: 2026-06-05 21:08 UTC 📊 Assets: 21 files 📝 What's New: <details open> opencl: improve getrows, cpy, concat and q6k flat gemv (#24160) opencl: allow multiple workgroups for large rows opencl: improve small cpy opencl: packed concat for small input opencl: tweak flat q6K gemv, increase NDST and remap threads </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9535 📅 Released: 2026-06-05 20:06 UTC 📊 Assets: 21 files 📝 What's New: <details open> common/chat : unify and fix LFM2/LFM2.5 tool parser (#24178) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9534 📅 Released: 2026-06-05 18:15 UTC 📊 Assets: 21 files 📝 What's New: <details open> vulkan: add fwht support for Intel with shmem reduction (#23964) vulkan: add fwht support for Intel with shmem reduction don't use N as workgroup size disable subgroup shuffle on MoltenVK AMD disable fwht shader on Intel Windows due to driver bug </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9533 📅 Released: 2026-06-05 17:27 UTC 📊 Assets: 21 files 📝 What's New: <details open> model: fix build failed (#24193) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9530 📅 Released: 2026-06-05 16:07 UTC 📊 Assets: 21 files 📝 What's New: <details open> cli: fix model params not propagated (#23893) Fixes #23847 </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 LangChain 🏷 Category: AI 🔖 Version: langchain-core==1.4.1 📅 Released: 2026-06-05 14:51 UTC 📊 Assets: 0 files 📝 What's New: Changes since langchain-core==1.4.0 release(core): 1.4.1 (#37922) fix(core): remove Bedrock prevalidation from load (#37909) docs(core): expand and link ModelProfile docstrings (#37904) release(anthropic): 1.4.4 (#37757) chore(core): bump uuid-utils to 0.16.0 (#37699) chore(infra): bump langchain-tests floor to 1.1.9 (#37610) release(standard-tests): 1.1.9 (#37609) chore: bump idna fro... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9524 📅 Released: 2026-06-05 09:17 UTC 📊 Assets: 21 files 📝 What's New: <details open> minor : fix lint issues (#24165) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9522 📅 Released: 2026-06-05 07:44 UTC 📊 Assets: 21 files 📝 What's New: <details open> kleidiai : dynamic chunck-based scheduling for hybrid execution (#23819) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release