OpenSourcePulse

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9707 📅 Released: 2026-06-19 00:26 UTC 📊 Assets: 25 files 📝 What's New: <details open> server: add "schema" and validation (#24150) wip working correct some limits add field name to error message </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED 📥 Download Release

🚀 New Release Alert! 📦 LangChain 🏷 Category: AI 🔖 Version: langchain-core==1.4.8 📅 Released: 2026-06-18 19:39 UTC 📊 Assets: 2 files 📝 What's New: Changes since langchain-core==1.4.7 chore: bump jupyter-server from 2.18.0 to 2.20.0 in /libs/core (#38252) chore: bump tornado from 6.5.6 to 6.5.7 in /libs/core (#38184) chore: bump bleach from 6.3.0 to 6.4.0 in /libs/core (#38198) release(core): 1.4.8 (#38254) refactor(langchain-classic): remove code for Python < 3.10 (#38194) perf(core): memoize BaseTool.tool_call_schema subset model and ... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9704 📅 Released: 2026-06-18 15:47 UTC 📊 Assets: 25 files 📝 What's New: <details open> server : return HTTP 400 on invalid grammar (#24144) (#24154) Throw on grammar parse failure so the server returns HTTP 400 instead of silently dropping the constraint. Add a regression test for the invalid-grammar response. Fixes #24144 </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9703 📅 Released: 2026-06-18 15:13 UTC 📊 Assets: 25 files 📝 What's New: <details open> server: (router) rework -hf preset repo (#24739) server: temporary remove HF remote preset rework remove preset.ini support rm unused get_remote_preset_whitelist() print warning add docs rm stray file </details> macOS/iOS: - macOS Apple Silicon (arm64) - ma... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9702 📅 Released: 2026-06-18 14:33 UTC 📊 Assets: 25 files 📝 What's New: <details open> server: fix router args not being forwarded to child instances (#24760) </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: b9701 📅 Released: 2026-06-18 13:39 UTC 📊 Assets: 1 files 📝 What's New: <details open> mtmd: refactor preprocessor, add mtmdimagepreprocout (#24736) * add mtmdimagepreprocout add dev docs remove unused clip API rm unused clip_image_f32_batch::grid change preprocess() call signature </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS ... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9698 📅 Released: 2026-06-18 09:25 UTC 📊 Assets: 25 files 📝 What's New: <details open> app : enable self-update only when built with llama-install.sh (#24754) Signed-off-by: Adrien Gallouët <angt@huggingface.co> </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9694 📅 Released: 2026-06-18 07:28 UTC 📊 Assets: 25 files 📝 What's New: <details open> ci : fix Windows x64 (OpenVINO) release link (#24731) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 FastAPI 🏷 Category: Backend Framework 🔖 Version: 0.137.2 📅 Released: 2026-06-18 06:57 UTC 📊 Assets: 0 files 📝 What's New: ### Features ✨ Add `iter_route_contexts()` for advanced use cases that used to use `router.routes` (e.g. Jupyverse). PR [#15785](https://github.com/fastapi/fastapi/pull/15785) by [@tiangolo](https://github.com/tiangolo). ### Translations 🌐 Fix broken Markdown in Korean custom response docs. PR #15774 by @kooqooo 📥 Download Release

🚀 New Release Alert! 📦 Ollama 🏷 Category: AI 🔖 Version: v0.30.10 📅 Released: 2026-06-17 16:22 UTC 📊 Assets: 17 files 📝 What's New: ## What's Changed models: add Cohere2MoE model by @jmorganca in https://github.com/ollama/ollama/pull/16670 llama: update llama.cpp to b9672 by @pdevine in https://github.com/ollama/ollama/pull/16775 Full Changelog: https://github.com/ollama/ollama/compare/v0.30.9...v0.30.10-rc0 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 claude-code 🏷 Category: Community Suggested 🔖 Version: v2.1.181 📅 Released: 2026-06-17 22:07 UTC 📊 Assets: 10 files 📝 What's New: ## What's changed - Added /config key=value syntax to set any setting from the prompt (e.g. /config thinking=false) — works in interactive, -p, and Remote Control - Added sandbox.allowAppleEvents opt-in setting that lets sandboxed commands send Apple Events on macOS - Added CLAUDE_CLIENT_PRESENCE_FILE environment variable: point it at a marker file to suppress mobile push notificatio... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9691 📅 Released: 2026-06-17 20:54 UTC 📊 Assets: 25 files 📝 What's New: <details open> ggml-cpu: Conditionally enable power11 backend based on compiler support (#24687) ggml: Conditionally enable power11 backend based on compiler support Guard POWER11 backend creation behind a compiler flag check for -mcpu=power11. This avoids build failures on current GCC/Clang toolchains while preserving forward compatibility once POWER11 support becomes available. Update... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 OpenFrontIO 🏷 Category: Community Suggested 🔖 Version: v0.32.0 📅 Released: 2026-06-17 17:40 UTC 📊 Assets: 0 files 📝 What's New: # v32 Release Notes ## Major Changes - New WebGL renderer — The entire game now renders on WebGL, which is faster and smoother (especially on big maps with lots of activity). It also comes with a new Graphics Settings modal with a dozen+ options so you can tweak how the game looks to your taste. - Higher trade-ship cap — Ports now spawn more trade ships before tapering off, s... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9686 📅 Released: 2026-06-17 17:31 UTC 📊 Assets: 25 files 📝 What's New: <details open> spec: fix segfault error on long prompts for eagle3 (#24707) </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: b9682 📅 Released: 2026-06-17 13:33 UTC 📊 Assets: 25 files 📝 What's New: <details open> vulkan: record actual memory properties during buffer creation (#24326) </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@6.4.8 📅 Released: 2026-06-17 14:10 UTC 📊 Assets: 0 files 📝 What's New: ### Patch Changes - #17109 `27c80ea` Thanks @ematipico! - Harden the limits on the number of decoding on the URL. 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9678 📅 Released: 2026-06-17 12:17 UTC 📊 Assets: 25 files 📝 What's New: <details open> opencl: optimize mulmatf16f32l4 for decode (#24504) </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: b9675 📅 Released: 2026-06-17 11:05 UTC 📊 Assets: 24 files 📝 What's New: <details open> sycl : Enable to support fp16 by OPs: SQR, SQRT, LOG, SIN, COS, CLAMP (#24692) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 Ollama 🏷 Category: AI 🔖 Version: v0.30.9 📅 Released: 2026-06-15 19:55 UTC 📊 Assets: 17 files 📝 What's New: ## What's Changed Support for Cohere2Moe architecture Fixed LFM2 parser/render for cases where thinking was not emitted Fixed issue where `ollama launch claude` and other coding agent or assistant use cases would only output one token Ollama will now return an error if a single message is larger than the current context window Full Changelog: https://github.com/ollama/ollama/... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 claude-code 🏷 Category: Community Suggested 🔖 Version: v2.1.179 📅 Released: 2026-06-16 20:22 UTC 📊 Assets: 10 files 📝 What's New: ## What's changed - Fixed mid-stream connection drops: partial responses are now preserved instead of showing a raw error, and the spinner no longer gets stuck at "running tool" - Fixed mouse-wheel scrolling in WSL2 under Windows Terminal and VS Code (regression in 2.1.172) - Fixed a sandbox denyRead/allowRead glob over a large directory tree making the Bash tool description enormous and t... 🔗 View on GitHub 📥 Download Release