OpenSourcePulse

🚀 New Release Alert! 📦 Next.js 🏷 Category: Frontend Framework 🔖 Version: v16.2.9 📅 Released: 2026-06-10 12:30 UTC 📊 Assets: 0 files 📝 What's New: Empty release to ensure next@latest points at a stable release. Next.js only allows publishing with Trusted Publishing enabled. In order to fix NPM dist-tags, we have to release a new version. Updating dist-tags is not possible with Trusted Publishing. 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9587 📅 Released: 2026-06-10 08:12 UTC 📊 Assets: 21 files 📝 What's New: <details open> speculative : fix "ngram-map-k4v" name in logging (#24253) This is a non-functional change. When using --spec-type ngram-map-k4v, the log messages at startup and runtime say ngram-map-k. Added logic in the in the constructor of common_speculative_impl_ngram_map_k to pass the correct COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V when config.key_only is false. After this ch... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 LangChain 🏷 Category: AI 🔖 Version: langchain-core==1.4.3 📅 Released: 2026-06-09 20:32 UTC 📊 Assets: 0 files 📝 What's New: Changes since langchain-core==1.4.2 release(core): 1.4.3 (#37991) feat(openai): support apply_patch built-in tool (#37157) 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 claude-code 🏷 Category: Community Suggested 🔖 Version: v2.1.170 📅 Released: 2026-06-09 17:23 UTC 📊 Assets: 10 files 📝 What's New: ## What's changed - Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Fable’s capabilities exceed those of any model we’ve ever made generally available. Update to version 2.1.170 for access. https://www.anthropic.com/news/claude-fable-5-mythos-5 - Fixed sessions not saving transcripts (and not appearing in --resume) when launched from the VS Code integrate... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9584 📅 Released: 2026-06-09 17:07 UTC 📊 Assets: 21 files 📝 What's New: <details open> ci : fix windows release (#24369) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 Astro 🏷 Category: Frontend Framework 🔖 Version: astro@6.4.5 📅 Released: 2026-06-09 12:46 UTC 📊 Assets: 0 files 📝 What's New: ### Patch Changes - #16985 `4ecff32` Thanks @maximslo! - Fixes the experimental.logger destination not being used for the "Server listening on..." startup message. The logger is now resolved before the server starts listening,... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 Grafana 🏷 Category: Monitoring 🔖 Version: 13.0.2 📅 Released: 2026-06-09 11:19 UTC 📊 Assets: 0 files 📝 What's New: Download page What's new highlights ### Features and enhancements - Dashboards: Show k8s format in provisioned save #123045, @stephaniehingtgen - Docker: Bump Alpine-based images to 3.23.4 #122938... 🔗 [View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9577 📅 Released: 2026-06-09 12:09 UTC 📊 Assets: 21 files 📝 What's New: <details open> server: log prompts to directory (#22031) server: log prompts to directory Add `--log-prompts-dir` to write each prompt to a separate text file in the specified directory. Apply suggestion from @ngxson --------- Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9574 📅 Released: 2026-06-09 09:09 UTC 📊 Assets: 21 files 📝 What's New: <details open> server : do not clear slots without unified KV cache (#24190) Always export idle slots to RAM Without this, a slot's VRAM cache may not be written to RAM. If this slot happens to be busy then later on, this triggers needless preprocessing in another slot. cont : clean-up --------- Co-authored-by: Christoph Weiss <weiss@wsoptics.de> Co-authored-by: Georgi Gerganov <gger... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9572 📅 Released: 2026-06-09 08:06 UTC 📊 Assets: 21 files 📝 What's New: <details open> ggml-cpu : fix rmsnormback wrong output under in-place aliasing (#24305) ggml-cpu : fix rms_norm_back wrong output under in-place aliasing cont : clean-up comment --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9570 📅 Released: 2026-06-09 04:16 UTC 📊 Assets: 21 files 📝 What's New: <details open> ggml-webgpu: Add clang-format job (#24308) Add clang-format job try local formatting </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 OpenFrontIO 🏷 Category: Community Suggested 🔖 Version: v0.32.0 beta 2 📅 Released: 2026-06-09 01:35 UTC 📊 Assets: 0 files 📝 What's New: Full renderer rewrite. 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 claude-code 🏷 Category: Community Suggested 🔖 Version: v2.1.169 📅 Released: 2026-06-08 21:57 UTC 📊 Assets: 10 files 📝 What's New: ## What's changed - Added --safe-mode flag (and CLAUDE_CODE_SAFE_MODE) to start Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting - Added /cd command to move a session to a new working directory without breaking the prompt cache mid-session - Added a disableBundledSkills setting and CLAUDE_CODE_DISABLE_BUNDLED_SKILLS env... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9568 📅 Released: 2026-06-08 21:10 UTC 📊 Assets: 21 files 📝 What's New: <details open> mtp: support for gemma-4 E2B and E4B assistants (#24282) models: update converter to support smaller assistants models: add maskedembd tensors to gemma4-assist arch * gemma-4: remove temp debug for conversion * gemma-4-mtp: filter out maskedembedding tensors during conversion </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 Ollama 🏷 Category: AI 🔖 Version: v0.30.7 📅 Released: 2026-06-07 21:51 UTC 📊 Assets: 17 files 📝 What's New: Ollama Launch now supports Hermes Desktop, a native desktop interface for the Hermes agent. Run it alongside your Hermes agent to get a visual interface for managing conversations, integrations, and messaging apps.

ollama launch hermes-desktop

<img width="2556" height="1716" alt="image" src="https://github.com/user-attachments/assets/3b2292d8-9f94-4d32-9023-85772e6ab3f8" /> Wha... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 LangChain 🏷 Category: AI 🔖 Version: langchain-core==1.4.2 📅 Released: 2026-06-08 18:19 UTC 📊 Assets: 0 files 📝 What's New: Changes since langchain-core==1.4.1 release(core): 1.4.2 (#37968) feat(core): deprecate problematic dict() method (#31685) 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9567 📅 Released: 2026-06-08 19:02 UTC 📊 Assets: 21 files 📝 What's New: <details open> server : do not parse when flushing http headers (#24281) </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: b9566 📅 Released: 2026-06-08 18:07 UTC 📊 Assets: 20 files 📝 What's New: <details open> graph: guard iswa kqmask on its own buffer (#24294) A SWA-only draft head (e.g. StepFun MTP) leaves the base sub-cache empty, so its kqmask buffer stays null and asserts at load. Guard each mask on its own buffer in setinput and canreuse, base and swa. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9564 📅 Released: 2026-06-08 17:08 UTC 📊 Assets: 0 files 📝 What's New: <details open> ggml-webgpu Implement 2D workgroups for scale, binary, and unary ops (#24044) Only run webgpu CI on my fork Add webgpu only workflow Implement 2d workgroups for more operations fix Fix type Move back to globalinvocationid </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9559 📅 Released: 2026-06-08 15:24 UTC 📊 Assets: 21 files 📝 What's New: <details open> cli: fix spinner not show during prompt processing (#24283) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release