OpenSourcePulse

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8798 📅 Released: 2026-04-15 08:50 UTC 📊 Assets: 25 files 📝 What's New: <details open> read nctx back after making llamacontext (#21939) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) - macOS Intel (x64)... 🔗 Repository: ggml-org/llama.cpp 📥 Download: b8798

🚀 New Release Alert! 📦 claude-code (Community Suggested) 🔖 Version: v2.1.109 📅 Released: 2026-04-15 04:02 UTC 📊 Assets: 0 files 📝 What's New: ## What's changed - Improved the extended-thinking indicator with a rotating progress hint 🔗 Repository: anthropics/claude-code 📥 Download: v2.1.109

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8796 📅 Released: 2026-04-15 02:20 UTC 📊 Assets: 25 files 📝 What's New: <details open> ggml : remove ggml-ext.h (#21869) ggml: correct placement of ggml-ext.h ggml : remove ggml-ext.h --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) ... 🔗 Repository: ggml-org/llama.cpp 📥 Download: b8796

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8795 📅 Released: 2026-04-14 23:29 UTC 📊 Assets: 25 files 📝 What's New: <details open> metal : fix FA support logic (#21898) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) - macOS Intel (x64) - iOS XCFram... 🔗 Repository: [ggml-org/llama.cpp 📥 Download: b8795

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8794 📅 Released: 2026-04-14 22:27 UTC 📊 Assets: 25 files 📝 What's New: <details open> mtmd: add mtmdimagetokensgetdecoderpos() API (#21851) * mtmd: add mtmdimagetokensgetdecoderpos() API consistent naming fix build </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) - macOS Intel (x64) 📥 Download: b8794

🚀 New Release Alert! 📦 LangChain (AI) 🔖 Version: langchain-core==1.2.29 📅 Released: 2026-04-14 20:45 UTC 📊 Assets: 0 files 📝 What's New: Changes since langchain-core==1.2.28 release(core): 1.2.29 and also port #36725 (#36727) 🔗 Repository: langchain-ai/langchain 📥 Download: langchain-core==1.2.29

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8793 📅 Released: 2026-04-14 21:10 UTC 📊 Assets: 25 files 📝 What's New: <details open> vulkan: Programmatically add RoundingModeRTE to all shaders when the device supports it (#21572) vulkan: Programmatically add RoundingModeRTE to all shaders when the device supports it use FetchContent to get SPIRV-Headers Fetch spirv-headers unconditionally remove fetchcontent, rely on installed headers fix ubuntu job Update docs/build.md </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download: b8793

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8792 📅 Released: 2026-04-14 19:51 UTC 📊 Assets: 25 files 📝 What's New: <details open> ci : re-enable mac workflows (#21894) ci : re-enable mac workflows vulkan : fix compile warning </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) - macOS Intel (x64) 📥 Download: b8792

🚀 New Release Alert! 📦 claude-code (Community Suggested) 🔖 Version: v2.1.108 📅 Released: 2026-04-14 19:12 UTC 📊 Assets: 0 files 📝 What's New: ## What's changed - Added ENABLE_PROMPT_CACHING_1H env var to opt into 1-hour prompt cache TTL on API key, Bedrock, Vertex, and Foundry (ENABLE_PROMPT_CACHING_1H_BEDROCK is deprecated but still honored), and FORCE_PROMPT_CACHING_5M to force 5-minute TTL - Added recap feature to provide context when returning to a session, configurable in /config and manually invocable with /recap; force with CLAUDE_CODE_ENABLE_AWAY_SUMMARY if telemetry disabled. - The model can now discover and invoke b... 🔗 Repository: anthropics/claude-code 📥 Download: v2.1.108

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8791 📅 Released: 2026-04-14 18:37 UTC 📊 Assets: 25 files 📝 What's New: <details open> metal : add XIELU unary op (#20802) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) - macOS Intel (x64) - iOS XCFramew... 🔗 Repository: [ggml-org/llama.cpp 📥 Download: b8791

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8790 📅 Released: 2026-04-14 17:52 UTC 📊 Assets: 25 files 📝 What's New: <details open> vendor : update BoringSSL to 0.20260413.0 (#21881) Signed-off-by: Adrien Gallouët <angt@huggingface.co> </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) - macOS Intel (x64) 📥 Download: b8790

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8789 📅 Released: 2026-04-14 16:49 UTC 📊 Assets: 25 files 📝 What's New: <details open> ggml : fix ARM NEON nvfp4 dot product on non-dotprod targets (#21559) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) - macOS Intel (x64) 📥 Download: b8789

🚀 New Release Alert! 📦 llama.cpp (AI) 🔖 Version: b8787 📅 Released: 2026-04-14 16:11 UTC 📊 Assets: 25 files 📝 What's New: <details open> ggml-webgpu: Update register tiling matmul to use f32 accumulation (#21644) Update register tiling matmul to use f32 accumulation fix profiling code Fix register tiling matmul for chrome, i'm blaming dawn Update batch tuning value for iOS compile fix Fix use of new load function </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm6... 🔗 Repository: [ggml-org/llama.cpp 📥 Download: b8787

🚀 New Release Alert! 📦 Laravel (Backend Framework) 🔖 Version: v13.2.0 📅 Released: 2026-04-14 14:39 UTC 📊 Assets: 0 files 📝 What's New: Remove axios and enable ignore-scripts by @WendellAdriel in https://github.com/laravel/laravel/pull/6778 Add /.cursor/ to .gitignore by @workwithbinu in https://github.com/laravel/laravel/pull/6782 Remove '.fleet' from .gitignore by @dominiq007 in https://github.com/laravel/laravel/pull/6783 Support all compose file naming conventions in editorconfig by @mmachatschek in https://github.com/laravel/laravel/pull/6786 🔗 Repository: laravel/laravel 📥 Download: v13.2.0

🚀 New Release Alert! 📦 Svelte (Frontend Framework) 🔖 Version: svelte@5.55.4 📅 Released: 2026-04-14 13:26 UTC 📊 Assets: 0 files 📝 What's New: ### Patch Changes - fix: never mark a child effect root as inert (#18111) - fix: reset context after waiting on blockers of @const expressions (#18100) - fix: keep flushing new eager effects (#18102) 🔗 Repository: sveltejs/svelte 📥 Download: svelte@5.55.4

🚀 New Release Alert! 📦 Grafana (Monitoring) 🔖 Version: 13.0.0 📅 Released: 2026-04-14 12:19 UTC 📊 Assets: 0 files 📝 What's New: Download page What's new highlights ### Features and enhancements - Chore: Prepare @grafana/sql for npm publishing #120786, @itsmylife - API Clients: Make legacy APIs internal only, and publish to NPM #119507, @tomratcliffe 📥 Download: v13.0.0

🆕 New Open-Source Repository 📦 GFW-knocker/MahsaNG 📝 a V2RayNG with Fragment , DoH , Rotating Configs , & free VPN servers ⭐ 2,627 stars | 🍴 270 forks | 💻 Kotlin | 📜 GPL-3.0 📅 Suggested by our community

🆕 New Open-Source Repository 📦 Rainman69/SNISPF 📝 SNISPF - Cross-Platform SNI Spoofing & DPI Bypass Tool ⭐ 44 stars | 🍴 15 forks | 💻 Python | 📜 MIT 📅 Suggested by our community

🚀 New Release Alert! 📦 claude-code (Community Suggested) 🔖 Version: v2.1.107 📅 Released: 2026-04-14 06:11 UTC 📊 Assets: 0 files 📝 What's New: ## What's changed - Show thinking hints sooner during long operations 🔗 Repository: anthropics/claude-code 📥 Download: v2.1.107

🚀 New Release Alert! 📦 Ollama (AI) 🔖 Version: v0.20.7 📅 Released: 2026-04-13 23:33 UTC 📊 Assets: 16 files 📝 What's New: ## What's Changed Fix quality of gemma:e2b and gemma:e4b when thinking is disabled ROCm: Update to ROCm 7.2.1 on Linux by @saman-amd in https://github.com/ollama/ollama/pull/15483 Full Changelog: https://github.com/ollama/ollama/compare/v0.20.6...v0.20.7 🔗 Repository: ollama/ollama 📥 Download: v0.20.7