OpenSourcePulse

🚀 New Release Alert! 📦 orbot-android 🏷 Category: Community Suggested 🔖 Version: Orbot for Android v17.9.5 BETA 3 (tor 0.4.9.9.1) 📅 Released: 2026-06-20 17:35 UTC 📊 Assets: 4 files 📝 What's New: 29edf4586 (HEAD -> master, tag: 17.9.5-BETA-3-tor-0.4.9.9, origin/master, origin/HEAD) updaet to 1795200300 cf58dc2df Merge branch 'master' of github.com:guardianproject/orbot 093f5e3f0 (tag: 17.9.5-BETA-2-tor-0.4.9.9) updaet to 1795200200 1fbfd7afc upgrade tor-android to 0.4.9.9 with fix for x86 dbdd1d1e0 make the event list mutable so we can add events to it 5c383d5ca update built in bri... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 android 🏷 Category: Community Suggested 🔖 Version: 5.0.4 📅 Released: 2026-06-20 17:23 UTC 📊 Assets: 6 files 📝 What's New: What's new: - Bugfix for auto tunnel rapid toggle SHA-256 fingerprints for the 4096-bit signing certificate:

5204d82e766e8aa14dcbb06dc70aebae2bdd812d4d6203cd521a8a685d7d3d80

To verify fingerprint:

apksigner verify --print-certs [path to APK file] | grep SHA-256

### Changelog ### :bug: Bug Fixes - `e5796d6` 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9739 📅 Released: 2026-06-20 15:29 UTC 📊 Assets: 25 files 📝 What's New: <details open> release: add missing link for win opencl adreno arm64 (#24809) </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: b9738 📅 Released: 2026-06-20 14:06 UTC 📊 Assets: 25 files 📝 What's New: <details open> server: avoid forwarding auth headers in CORS proxy (#24373) server: avoid forwarding auth headers in CORS proxy format fix test fix e2e test --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co> </details> macOS/iOS: - macOS Apple Silicon (arm64) - ma... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9733 📅 Released: 2026-06-20 00:16 UTC 📊 Assets: 25 files 📝 What's New: <details open> ggml-webgpu: add adapter toggles for F16 on Vulkan + NVIDIA </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: b9731 📅 Released: 2026-06-19 21:54 UTC 📊 Assets: 25 files 📝 What's New: <details open> server : optimize gettokenprobabilities (#24796) Use std::partialsort to order only the requested top-n tokens instead of the full vocabulary logprobs sort: vocab=128000 ntop=0 iters=100 full sort: 8555.6 us/op partial sort: 704.3 us/op Signed-off-by: Adrien Gallouët <angt@huggingface.co> </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9729 📅 Released: 2026-06-19 20:47 UTC 📊 Assets: 25 files 📝 What's New: <details open> server: remove all internal mentions about "webui" (#24817) </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: b9728 📅 Released: 2026-06-19 16:19 UTC 📊 Assets: 25 files 📝 What's New: <details open> arg: Add comment line support to --api-key-file (#23168) </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: b9727 📅 Released: 2026-06-19 15:45 UTC 📊 Assets: 25 files 📝 What's New: <details open> vendor : update cpp-httplib to 0.48.0 (#24787) </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: b9721 📅 Released: 2026-06-19 08:09 UTC 📊 Assets: 25 files 📝 What's New: <details open> sync : ggml </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: b9716 📅 Released: 2026-06-19 03:55 UTC 📊 Assets: 25 files 📝 What's New: <details open> mtmd: add batching support for internvl (#24775) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 rethink-app 🏷 Category: Community Suggested 🔖 Version: v0.5.5x 📅 Released: 2026-06-19 01:54 UTC 📊 Assets: 5 files 📝 What's New: ### 💤 Zzzzz 3 - Improvement: Global / user-preferred DNS (set in Configure -> DNS -> Type) works alongside Simple-mode WireGuard, regardless of Configure -> DNS -> Split DNS setting. - Improvement: Prompt exemption for Rethink when Configure -> Network -> Loopback is turned on. - Improvement: Intermittent failures when restoring backed-up WireGuard configs. - Fix: Both WiF... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9713 📅 Released: 2026-06-19 02:26 UTC 📊 Assets: 25 files 📝 What's New: <details open> mtmd: add batching for mtmd-cli, add video tests (#24778) </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: v2.1.183 📅 Released: 2026-06-19 01:20 UTC 📊 Assets: 10 files 📝 What's New: ## What's changed - Improved auto mode safety: destructive git commands (git reset --hard, git checkout -- ., git clean -fd, git stash drop) are now blocked when you didn't ask to discard local work, git commit --amend is blocked when the commit wasn't made by the agent this session, and terraform destroy/pulumi destroy/cdk destroy are blocked unless you asked for the specific ... 🔗 View on GitHub 📥 Download Release

🚀 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