Hero Image
Articles

懷舊遊戲 See exactly what changed between two 3D models Github episteme: A multi-platform document and e-book reader. VictoriaMetrics: fast, cost-effective monitoring solution and time series database palmier-pro: macOS video editor built for AI A web browser extension for Chrome, Firefox, Edge, and Safari 14. Open-source credential gateway with a built-in vault. give your AI agents access to services without exposing keys. Desktop app to generate 3D models from images using local AI — runs entirely on your GPU darktable is an open source photography workflow application and raw developer Privacy oriented video player for iOS, tvOS and macOS Examples in the MLX framework Container registry which transparently builds images using the Nix package manager. Self-Hosted ReClip: Download videos from almost any website. Lightweight, self-hosted media downloader with a clean web UI. Sync-in Server · Sovereign platform for file storage, sharing, synchronization, and collaboration. 🏖️ A serverless, open-source file hosting solution built on Cloudflare. Supports image hosting, secure file storage, and personal cloud drive capabilities. FUSE-based file system for replicating SQLite databases across a cluster of machines A Go-based API that acts as a bridge to the ComfyUI backend Skill Skills for teaching agents how to build on Cloudflare. everything claude code: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端 An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms Article https://pkg.go.dev/golang.org/x/tools/go/analysis Go 语言技能：AI 时代的 Go 开发工具链

Friday, August 7, 2026 閱讀
Hero Image
Local LLM on MacBookPro - Audio/Video

Video https://huggingface.co/Wan-AI https://github.com/Wan-Video/Wan2.2 https://github.com/Blaizzy/mlx-video https://huggingface.co/fishaudio/s2-pro Install uv tool install git+https://github.com/Blaizzy/mlx-video.git Download Model HF_HUB_DISABLE_XET=1 hf download Wan-AI/Wan2.2-TI2V-5B --local-dir Wan2.2-TI2V-5B --max-workers 1 HF_HUB_DISABLE_XET=1 hf download Wan-AI/Wan2.2-T2V-A14B --local-dir Wan2.2-T2V-A14B --max-workers 1 Convert ~/.local/share/uv/tools/mlx-video/bin/python -m mlx_video.models.wan_2.convert \ --checkpoint-dir models/Wan-AI/Wan2.2-TI2V-5B \ --output-dir models/Wan-AI/Wan2.2-TI2V-5B-mlx ~/.local/share/uv/tools/mlx-video/bin/python -m mlx_video.models.wan_2.convert \ --checkpoint-dir models/Wan-AI/Wan2.2-T2V-A14B \ --output-dir models/Wan-AI/Wan2.2-T2V-A14B-mlx \ --dtype bfloat16 Run Wan2.2-TI2V-5B t2v mlx_video.wan_2.generate \ --model-dir models/Wan-AI/Wan2.2-TI2V-5B-mlx \ --prompt 'A cinematic aerial shot of the Great Wall of China at sunrise' \ --width 1280 \ --height 704 \ --num-frames 81 \ --steps 40 \ --guide-scale 5.0 \ --shift 5.0 \ --scheduler unipc \ --seed 3478 \ --output-path video/great_wall1.mp4 i2v mlx_video.wan_2.generate \ --model-dir models/Wan-AI/Wan2.2-TI2V-5B-mlx \ --prompt 'A cat is boating on the river' \ --image models/Wan-AI/Wan2.2-TI2V-5B/examples/i2v_input.JPG \ --width 1280 \ --height 704 \ --num-frames 81 \ --steps 40 \ --guide-scale 5.0 \ --shift 5.0 \ --scheduler unipc \ --seed 13633 \ --output-path video/cat.mp4 Wan2.2-T2V-A14B mlx_video.wan_2.generate \ --model-dir models/Wan-AI/Wan2.2-T2V-A14B-mlx \ --prompt 'A cinematic aerial shot of the Great Wall of China at sunrise' \ --width 1280 \ --height 720 \ --num-frames 81 \ --steps 40 \ --guide-scale 3.0,4.0 \ --shift 12.0 \ --scheduler unipc \ --seed 11846 \ --output-path video/great_wall2.mp4 Upload HF_HUB_DOWNLOAD_TIMEOUT=120 HF_HUB_DISABLE_XET=1 hf upload-large-folder rickylin20260522/Wan2.2-TI2V-5B-mlx models/Wan-AI/Wan2.2-TI2V-5B-mlx --repo-type model --num-workers 2 Audio https://huggingface.co/MediaTek-Research Install brew install ffmpeg uv pip install mlx mlx-audio Convert model python -m mlx_audio.convert \ --hf-path models/MediaTek-Research/Breeze-ASR-25 \ --mlx-path models/MediaTek-Research/Breeze-ASR-25-mlx \ --dtype bfloat16 \ --model-domain stt audio ffmpeg \ -i ~/Downloads/talk.m4a \ -ar 16000 \ -ac 1 \ -c:a pcm_s16le \ ~/Downloads/talk.wav Run STT

Friday, July 31, 2026 閱讀
Hero Image
Local LLM on MacBookPro - Image

https://huggingface.co/mlx-community https://github.com/filipstrand/mflux https://github.com/lpalbou/mlx-gen https://huggingface.co/AbstractFramework Install uv tool install --upgrade mflux uv tool install --upgrade --force mlx-gen Download Model # mlx-community/FLUX.2-klein-9B # AbstractFramework/z-image-turbo-8bit # AbstractFramework/qwen-image-edit-2511-8bit HF_HUB_DISABLE_XET=1 hf download mlx-community/FLUX.2-klein-9B --local-dir FLUX.2-klein-9B --max-workers 1 Run FLUX.2-klein-9B mflux-generate-flux2 \ --model "/Users/ricky/git/mlx/FLUX.2-klein-9B" \ --prompt 'Charmander from Pokemon, a specific Nintendo character, iconic appearance, very clean large eyes, friendly wide smile, smooth round belly, long distinct tail with simple flame outlines' \ --steps 6 \ --seed 42 \ --width 1240 \ --height 1754 \ --output pics/charmander.png z-image-turbo-8bit mlxgen generate \ --model /Users/ricky/git/mlx/z-image-turbo-8bit \ --prompt '哆啦Ａ夢使用竹蜻蜓飛在天空中' \ --steps 6 \ --seed 42 \ --width 1240 \ --height 1754 \ --output pics/doramon.png qwen-image-edit-2511-8bit mlxgen generate \ --model /Users/ricky/git/mlx/qwen-image-edit-2511-8bit \ --prompt '哆啦Ａ夢使用竹蜻蜓飛在天空中，旁邊有大雄' \ --steps 6 \ --seed 42 \ --width 1240 \ --height 1754 \ --image-path pics/doramon.png \ --output pics/doramon1.png

Saturday, June 20, 2026 閱讀
Hero Image
Local LLM on MacBookPro

https://huggingface.co/mlx-community https://github.com/ml-explore/mlx-lm https://github.com/jundot/omlx Install # install hf uv tool install "huggingface_hub" --with hf-xet --upgrade hf auth login hf auth whoami # install mlx_lm uv tool install --force \ --from 'git+https://github.com/ml-explore/mlx-lm.git@refs/pull/1192/head' mlx-lm \ --with 'transformers @ git+https://github.com/huggingface/transformers.git' # install mlx-openai-server uv pip install git+https://github.com/cubist38/mlx-openai-server.git --system # install [litellm](https://github.com/BerriAI/litellm) uv tool install 'litellm[proxy]' # install [claw-code](https://github.com/ultraworkers/claw-code) cargo install agent-code Download Model HF_HUB_DISABLE_XET=1 hf download mlx-community/DeepSeek-V4-Flash-4bit \ --local-dir deepseekV4 --repo-type model Run Server mlx_lm.server --model /Users/ricky/git/mlx/deepseekV4 --port 8080 or

Monday, June 1, 2026 閱讀