Tool Watch
Tools that keep showing up
Every briefing tracks the open tools and model repos a creator can actually run on their own machine. This board aggregates them over time, because a single appearance is noise and a repeat appearance is a decision you can plan around.
133 tools on the board 44 briefings counted Open weights and local-first only
| Repo | What it is | Days | First | Last |
|---|---|---|---|---|
| comfyanonymous/ComfyUI | ](https://github.com/comfyanonymous/ComfyUI): 135k stars. | 9 | Aug 27 | Sep 24 |
| Lightricks/LTX-2 | The license text that decides whether your LTX-2.5 renders are commercially usable, which for most readers here they are | 6 | Aug 27 | Sep 4 |
| hao-ai-lab/FastVideo | The toolkit that runs FastH3 V2, now with a single-card consumer path. | 5 | Aug 27 | Oct 6 |
| OpenVDN/vdn-minimax-h3 | Hybrid-attention H3 with all four training stages published, climbing steadily all week (389) | 5 | Sep 5 | Sep 9 |
| storytold/artcraft | The same team's AI image and video studio; FilmCraft and PhotoCraft are standalone sibling apps. | 4 | Oct 5 | Oct 10 |
| storytold/photocraft | The Photoshop rebuild that started the storytold run, now 21k stars per shields.io, up from 11k yesterday | 4 | Oct 5 | Oct 8 |
| leejet/stable-diffusion.cpp | The no-Python image runtime behind today's Ming-Image conversion. | 4 | Aug 31 | Oct 3 |
| city96/ComfyUI-GGUF | Loads GGUF-quantized diffusion checkpoints, the standard low-VRAM path (4k) | 4 | Aug 28 | Sep 1 |
| OpenCut-app/OpenCut | The open-source CapCut alternative, still the obvious place to cut everything above. | 3 | Oct 4 | Oct 6 |
| Comfy-Org/ComfyUI | 136k stars per shields.io; none of today's releases ship ComfyUI files yet, so expect community wrappers | 3 | Sep 22 | Oct 3 |
| nunchaku-tech/nunchaku | The four-bit runtime both ModelsLab builds are packed for, and the reason the speedup exists at all rather than just the file shrinking (repo, 4k stars per shields.io). | 3 | Sep 6 | Sep 21 |
| ostris/ai-toolkit | Still the trainer under most community video LoRAs shipping this week (12k) | 3 | Sep 7 | Sep 9 |
| T8mars/comfyui-minimax-h3-audio-T8 | The H3 node pack this ecosystem's ComfyUI side routes through (956) | 3 | Sep 4 | Sep 6 |
| kijai/ComfyUI-KJNodes | Utility pack whose Low VRAM Attention node is a hard dependency for the 1080p recipe above (3.2k) | 3 | Aug 28 | Sep 1 |
| storytold/filmcraft | Free open Premiere-style editor in Rust with an MCP server so an AI agent can drive every command. | 2 | Oct 7 | Oct 10 |
| ddalcu/mlx-serve | Free Mac app; ddalcu's new pack card (not yet the README) says version 26.10.2 serves Qwen-Image-2.1-Turbo, 4-bit sized for 16 GB Macs. Turbo packs posted October 9; 1.8k stars (shields.io). | 2 | Oct 9 | Oct 10 |
| Yzmblog/DMAD | Code and the new 24 GB ComfyUI workflows for four-step MiniMax H3 | 2 | Oct 3 | Oct 8 |
| Lightricks/ComfyUI-LTXVideo | Home of the IC-LoRA workflow the Alpha-Gen matte runs on. | 2 | Aug 28 | Oct 7 |
| neilsonnn/image-blaster | One photo in, an explorable 3D scene out, run through Claude Code. | 2 | Oct 4 | Oct 5 |
| aigc-apps/VideoX-Fun | The inference code for the new eight-condition control branch. | 2 | Sep 2 | Sep 23 |
| antirez/h3.c | From-scratch C and Metal MiniMax H3 for Apple Silicon, still the best-documented speed-quality tradeoff table in the category (2.6k) | 2 | Sep 8 | Sep 9 |
| Eliovp-BV/paiton-vllm-plugin | The ROCm container stack and launch script behind today's single-Radeon MiniMax H3 release, and the same repo that shipped the RDNA4 FLUX.2 Klein package two days ago (0) | 2 | Sep 8 | Sep 9 |
| james-see/ltx-video-mac | MIT SwiftUI front end that puts LTX-2, 2.3, 2.5 and H3 behind one model picker and a localhost REST API (400) | 2 | Aug 30 | Sep 8 |
| dgrauet/ltx-2-mlx | The MLX runtime the LTX-2.5 pack is built for, distilled 8-step and dev two-stage (109) | 2 | Aug 30 | Sep 8 |
| hradec/ComfyUI-HR-Endless-Sampler | Arbitrary-length H3 video on a 16 GB card with a language model directing continuity between chunks (74, up from 72 yesterday) | 2 | Sep 1 | Sep 2 |
| Wan-Video/Wan2.2 | The Apache 2.0 video family Matrix-Game 3.5 is built on top of (17k) | 2 | Aug 31 | Sep 1 |
| ml-explore/mlx | Apple's array framework, what the Mac conversions run on (28k) | 2 | Aug 30 | Aug 31 |
| NVlabs/Sana | Home of the four-step 720p video model above (8.9k) | 2 | Aug 27 | Aug 29 |
| akatz-ai/h3-relay | ComfyUI nodes that build long MiniMax H3 shots from short windows and let you reroll one window without redoing the ones you liked. Why now: it is the reroll engine behind the Person Remover; 21 stars (repo, GPL-3.0 for the code only). | 1 | Oct 11 | Oct 11 |
| ARahim3/DigUp | A free Mac app that finds photos, recordings and video in folders you choose by describing them, fully offline. | 1 | Oct 11 | Oct 11 |
| calesthio/OpenMontage | An agent-driven video production kit with eleven pipelines (explainer, documentary montage, talking head, dub) that can run free with local narration and open archives. Why now: on Trendshift's daily list; 66k stars (repo, AGPL-3.0). | 1 | Oct 11 | Oct 11 |
| Jakubantalik/transitions.dev | Copy-ready interface transitions (modal open, card resize, error shake) for web motion work. | 1 | Oct 11 | Oct 11 |
| wheresryan22/anatomy | A Claude skill that explains an idea by drawing it as an interactive isometric machine in SVG, with WebGL and 3D options. | 1 | Oct 11 | Oct 11 |
| sirioberati/Genjustsu-Open-Source-Workflow | Local app that swaps the subject in a video while keeping the scene and soundtrack, using hosted models, no GPU needed. | 1 | Oct 10 | Oct 10 |
| tlack/babytalk | Offline speech-to-text and text-to-speech on an ESP32-S3 or ESP32-P4 board (16 MB flash, 8 MB PSRAM), for talking props and installations. Show HN October 9; 18 stars. | 1 | Oct 10 | Oct 10 |
| speridlabs/iris-3b | Apache image model plus depth and 4x restore from one backbone, with code. | 1 | Oct 9 | Oct 9 |
| thesnarkitecht/rembrandt | Free raw developer with local AI masks and denoise. | 1 | Oct 9 | Oct 9 |
| yi1108/printfilm | Self-hosted pipeline that turns a script into storyboard, images, video and a final cut for short dramas, MIT, Chinese docs, needs a paid upstream key. On Trendshift's daily list, tagged new; 5.1k stars. | 1 | Oct 9 | Oct 9 |
| T8mars/Comfyui-Prism-T8 | ComfyUI nodes that run Prism's joint video-and-audio pipeline. | 1 | Oct 9 | Oct 9 |
| ywbn/VoTSpeech | Instruction-driven voice design code, non-commercial weights. | 1 | Oct 9 | Oct 9 |
| robbietilton/Compositor | A free MIT image editor for Apple-silicon Macs with layers, masks, adjustment layers, Select Subject and Content-Aware Fill; opens PSD and PSB (8-bit RGB only, no CMYK) but exports JPEG only. Released September 16; 12k stars per shields.io | 1 | Oct 8 | Oct 8 |
| storytold/vectorcraft | An Illustrator-style vector app in Rust with SVG, PDF and PDF-compatible .ai import and export. | 1 | Oct 8 | Oct 8 |
| shader-effects-inc/shaders | 200+ animated web effects (glass, metal, noise, gradients) you design on a free canvas and export as code for React, Vue, Svelte or plain JavaScript; the library is MIT, the Framer plugin is in the paid tier. 3.1k stars per shields.io | 1 | Oct 8 | Oct 8 |
| storytold/effectcraft | An After Effects-style compositor with 306 effects and Lottie support; first commit October 1, and the README says it "isn't yet a replacement for After Effects on client work." Cannot open .aep files. 1.1k stars per shields.io | 1 | Oct 7 | Oct 7 |
| storytold/lightcraft | A Lightroom-style library and raw developer at about 79% by feature count, though the README puts it nearer 60 to 70% as a day-to-day Lightroom replacement; CR3 or compressed Fujifilm raws open only as embedded previews, and its "AI masks" are classical heuristics. 1.8k stars per shields.io | 1 | Oct 7 | Oct 7 |
| kandinskylab/kandinsky-6 | Code for today's lead, picture plus sound under MIT. | 1 | Oct 7 | Oct 7 |
| KittenML/KittenTTS | The library behind the CPU voice cloner above. | 1 | Oct 7 | Oct 7 |
| allenv0/SCM | Search every photo and every frame of video in a folder by describing it, with jumps to the timecode, plus search by on-screen text and spoken dialogue. Repo created October 3, Show HN on October 4 (166 points at last check), MIT, 389 stars per shields.io | 1 | Oct 6 | Oct 6 |
| Tencent-Hunyuan/Prism | Code for the 2K picture-plus-sound model above. | 1 | Oct 6 | Oct 6 |
| chenkangjie1123/VGGT-Diff | Code for the six-photo new-angle research above. | 1 | Oct 5 | Oct 5 |
| zcbacxc/movie-narrator | Give it a film and a style, get a narrated recap video with subtitles. | 1 | Oct 4 | Oct 4 |
| meituan-longcat/LongCat-Video | Meituan's open video generation model. | 1 | Oct 4 | Oct 4 |
| modelscope/DiffSynth-Studio | The Python toolkit PixelTune is tested with, and the route to run it locally. | 1 | Oct 4 | Oct 4 |
| takakhoo/audio-diffusion-control | 35 sliders that change one quality of an AI music clip without changing the piece. | 1 | Oct 3 | Oct 3 |
| anteloc/ldraw-nova | Describe a LEGO model, get LDraw and Blender files back. | 1 | Oct 3 | Oct 3 |
| ace-step/ACE-Step-1.5 | The MIT music model the sliders ride on, 10 seconds to 10 minutes per song. | 1 | Oct 3 | Oct 3 |
| sakasegawa/irodori-tts-ggml | Japanese voice cloning that runs on Metal, Vulkan or CUDA in about 2 GB. | 1 | Oct 2 | Oct 2 |
| Bonenk/OmniVoice-GGUF | Multilingual voice cloning and voice design in about 1.62 GB for the CrispASR runtime, cloning gated behind a consent attestation. Created October 2; CC BY-NC, so no paid work (card). | 1 | Oct 2 | Oct 2 |
| Avdpro/FlashHead-Pro-MLX | Photo plus audio to a 512 × 512 talking-head video on Apple Silicon, 6.92 GB, no PyTorch needed, Apache 2.0. | 1 | Oct 2 | Oct 2 |
| sorge89/FLUX.2-klein-4B-onnx | The Apache 2.0 Klein 4B image model in about 7.84 GB for ONNX Runtime on CPU, CUDA or DirectML, so Windows users on AMD or Intel graphics have a path. Created October 1 (card). | 1 | Oct 2 | Oct 2 |
| ideogram-oss/ideogram-4 | The open Ideogram 4.0 repo (2.9k stars per shields.io) is where 4.5's promised weights should land; watch it | 1 | Oct 2 | Oct 2 |
| Work-Fisher/MiniMax-H3-Wuxia-Fight-Workflow | A two-pass fight-scene workflow with a cancel-early draft, tested on a 12 GB card. | 1 | Oct 1 | Oct 1 |
| Iwannapose/minimax_h3_pdmd_2nfe_comfyui | Two-step H3 video inside stock ComfyUI. | 1 | Oct 1 | Oct 1 |
| OzzyGT/minimax_h3_preview_blocks | See each step of an H3 generation and abort bad runs. | 1 | Oct 1 | Oct 1 |
| speach1sdef178/MiniMax-H3-X2-Detail-VAE | 2x-resolution H3 decoding in ComfyUI, with an honest write-up of what failed. | 1 | Oct 1 | Oct 1 |
| becausereasons/yue2-grvl-raspy-rock-soul | Six vocal-style add-ons for open song generation, with demos. | 1 | Oct 1 | Oct 1 |
| markldn/Dia2-2B-GGUF | Dia2 voices on AMD and CPU. | 1 | Oct 1 | Oct 1 |
| kyutai/ovie-512 | A 512-pixel version of Kyutai's single-photo new-camera-angle model, MIT license, from a March paper. | 1 | Oct 1 | Oct 1 |
| inclusionAI/Ming-Image | ](https://github.com/inclusionAI/Ming-Image): the code, the ten transparency phrases, and both published prompt rewriters for design generation and layer decomposition. 93 stars, which means early (shields.io, checked today). | 1 | Sep 25 | Sep 25 |
| Comfy-Org/Ming-Image | ](https://huggingface.co/Comfy-Org/Ming-Image): ComfyUI's own packaging of both Ming models including layer-specific weight files, created September 24 (createdAt 2026-09-24T07:13:14Z). The pull request wiring it into ComfyUI is open and not merged, so the files are there and the graph is not. Two community Spaces are already pulling from it. | 1 | Sep 25 | Sep 25 |
| AlibabaResearch/SparkDiffusion | ](https://github.com/AlibabaResearch/SparkDiffusion): four-step, heavily sparse Wan2.1 and Wan2.2 checkpoints under Apache 2.0. 139 stars. | 1 | Sep 25 | Sep 25 |
| NVIDIA-NeMo/Speech | ](https://github.com/NVIDIA-NeMo/Speech): the toolkit that runs the diarization model, plus the end-to-end evaluation script. 19k stars. | 1 | Sep 25 | Sep 25 |
| vpakarinen/better-human-motion-h3-lora | ](https://huggingface.co/vpakarinen/better-human-motion-h3-lora): an Apache 2.0 add-on for MiniMax-H3 aimed at human movement, created September 2 and still climbing, with a free demo Space. Its sibling natural-face-speech-h3-lora targets talking faces. | 1 | Sep 25 | Sep 25 |
| JOKER141/BUNNY_H3_Conditioning_Bridge | ](https://huggingface.co/JOKER141/BUNNYH3ConditioningBridge): an action-continuity adapter for MiniMax-H3 with an Example Workflow.json in the repo, created September 13. Licence is the MiniMax-H3 community agreement, not an open one, so check it before commercial use. | 1 | Sep 25 | Sep 25 |
| Comfy-Org/workflow_templates | ](https://github.com/Comfy-Org/workflowtemplates): 991 stars. | 1 | Sep 24 | Sep 24 |
| Comfy-Org/ComfyUI-Manager | ](https://github.com/Comfy-Org/ComfyUI-Manager): 16k stars. | 1 | Sep 24 | Sep 24 |
| huggingface/diffusers | ](https://github.com/huggingface/diffusers): 35k stars. | 1 | Sep 24 | Sep 24 |
| huggingface/lerobot | ](https://github.com/huggingface/lerobot): 28k stars. | 1 | Sep 24 | Sep 24 |
| black-forest-labs/flux-action | ](https://github.com/black-forest-labs/flux-action): 25 stars. | 1 | Sep 24 | Sep 24 |
| HyperGAN/supra-particle-sliders | Training and inference scripts for concept dials on the tiny Supra image model, with timing evidence as JSON Why now: published Wednesday alongside the weights. | 1 | Sep 23 | Sep 23 |
| HyperGAN/krea2-particle-sliders | The same recipe against Krea 2 Turbo, with a ComfyUI node and setup guide Why now: the Krea sliders posted a few minutes after the Supra pair. | 1 | Sep 23 | Sep 23 |
| ali-vilab/VACE | Not new, but it is the preprocessing dependency for the new Layout condition. | 1 | Sep 23 | Sep 23 |
| TencentARC/WorldCrafter | Camera-steered video world model that remembers what it already drew (link, 150 stars). | 1 | Sep 22 | Sep 22 |
| cseti007/ComfyUI-CrossViewWarp | The orbit picker and live preview that build the depth warp; Apache 2.0, no extra packages required (link, 59 stars). | 1 | Sep 22 | Sep 22 |
| mimbres/spansynth-edit | MIDI-guided synthesis and span editing of real recordings, Apache 2.0, runs on a laptop GPU (link). | 1 | Sep 22 | Sep 22 |
| SupraLabs/Supra2-IMG | A 417 MB image model and the script that made it, for anyone studying small-scale pretraining (link). | 1 | Sep 22 | Sep 22 |
| ModelTC/LightX2V | Day-zero acceleration for Qwen-Image-2.1, aimed at consumer cards as well as datacenter ones (usage guide, 2.8k stars). | 1 | Sep 21 | Sep 21 |
| QwenLM/Qwen-Image-2.1 | The reference code, prompt-rewriting scripts and the licence you are agreeing to (repo, 770 stars). | 1 | Sep 21 | Sep 21 |
| realrebelai/LOW_VRAM_Workflows | ComfyUI graphs stress-tested against an 8 GB card with 16 GB of system memory, Apache 2.0, updated Monday morning (repo, 52 likes). | 1 | Sep 21 | Sep 21 |
| xiaol/LiuBai-RWKV | The music model above, with its dated experiment log (code repo, 1 like on the weights repo, brand new). | 1 | Sep 21 | Sep 21 |
| Tencent-Hunyuan/AuK | One instruction box that does TTS, voice cloning, denoising, stem separation and speech editing, MIT licensed. | 1 | Sep 12 | Sep 12 |
| Saganaki22/ComfyUI-AuK | Eight nodes, three drag-and-drop workflows, and the reliability ranking that should ship with every model. | 1 | Sep 12 | Sep 12 |
| vanch007/mlx-AuK | Native Apple Silicon port with an A/B web demo, Flash and Base weights posted September 12. | 1 | Sep 12 | Sep 12 |
| AlayaLab/Evoke | Three-step world model plus the Director UI for per-chunk prompting and dual-stick camera. | 1 | Sep 12 | Sep 12 |
| ngquocvinh/YuE2-3B-GGUF | Full song generation on a 6.4 GB peak instead of an 11 GB one, with the measurement table to prove it (card). | 1 | Sep 12 | Sep 12 |
| TeamAudiyo/MM3-GGUF | MiniMax-Music3 quantized to 1.49 GB for 8-10 GB cards, Apache-2.0 inherited (card). | 1 | Sep 12 | Sep 12 |
| onnx-community/VibeVoice-Realtime-0.5B-Onnx | Streaming long-form TTS in ONNX Runtime, MIT, posted September 11 (card). | 1 | Sep 12 | Sep 12 |
| multimodal-art-projection/YuE | The codebase behind the day's music release, now carrying YuE2's editable-score pipeline. | 1 | Sep 10 | Sep 10 |
| Eyeline-Labs/ID-V2V | Restyle a shot without re-filming it, with five documented recipes and a runnable sample folder for each. | 1 | Sep 10 | Sep 10 |
| Soul-AILab/SoulX-FlashHead | Real-time streaming talking heads on one RTX 4090, 1.1k stars. | 1 | Sep 10 | Sep 10 |
| m-a-p/SheetSage2 | A 57.2M-parameter transcriber that turns a recording into ABC notation and MIDI, and ships an abcjs renderer plus a piano soundfont so it can draw and play the result. CC BY-NC 4.0 (weights). | 1 | Sep 10 | Sep 10 |
| microsoft/webnn-developer-preview | Hosts the free browser Z-Image Turbo demo and the reference WebNN pipeline behind it (69) | 1 | Sep 9 | Sep 9 |
| kohya-ss/musubi-tuner | Named by name in several of the Krea 2 character LoRAs published September 8 (2k) | 1 | Sep 9 | Sep 9 |
| resemble-ai/chatterbox | The MIT voice-cloning base that loudr-1 and its turbo student descend from (26k) | 1 | Sep 7 | Sep 7 |
| thewh1teagle/kokoro-onnx | Source of the redistributed Kokoro voice vectors, and still the reference for running the model off Apple's stack (2.7k) | 1 | Sep 7 | Sep 7 |
| caguilar-dev/moss-soundeffect-coreai | Conversion recipes, tests and the Swift runtime for the MOSS bundle, including a patch against Apple's BSD-3-Clause coreai-models runtime (0) | 1 | Sep 7 | Sep 7 |
| JoaoZaokk/comfy-quant-bench | The harness behind the three-build Wan comparison, and the only place this week where somebody wrote a prediction down before measuring and then published being wrong (2) | 1 | Sep 6 | Sep 6 |
| breezeblue-ai/breeze-tts | Apache 2.0 inference code for Breeze TTS 2, voice design and voice direction included (285) | 1 | Sep 6 | Sep 6 |
| t8star/Vdn-Minimax-H3-Comfy | Went up September 3 as a drop-in bundle already using ComfyUI's folder names, pinned to a specific OpenVDN revision. | 1 | Sep 5 | Sep 5 |
| RealRebelAI/LLaDa-Image_ComfyUI | Nodes for diffusion-language image generation and instruction editing from one checkpoint | 1 | Sep 5 | Sep 5 |
| google/spatial-media | The unglamorous dependency both VR LoRAs need, because a 2:1 mp4 without spherical metadata is just a squashed rectangle | 1 | Sep 5 | Sep 5 |
| inclusionAI/LLaDA-Image | Upstream source and documentation for the editing path the ComfyUI nodes wrap | 1 | Sep 5 | Sep 5 |
| CreativeMayhemLtd/provcheck | Watermark and C2PA-sign your generated media inside the graph, offline, tied to your Bluesky handle if you want it (11) | 1 | Sep 4 | Sep 4 |
| Danzer1xxxxChan/H3-World | The upstream code for the action-control LoRA, if you want to train your own action set rather than use the shipped one | 1 | Sep 4 | Sep 4 |
| jd-opensource/JoyAI-Echo | Source and example camera trajectories for Echo-WM, including the wmcausalcases inputs the Diffusers card uses | 1 | Sep 4 | Sep 4 |
| OpenMOSS/MOSS-TTS | Apache 2.0 code for the sound-effects model, including the Gradio demo and fine-tuning recipes | 1 | Sep 4 | Sep 4 |
| OpenShot/openshot-qt | Free GPLv3 editor that now does local subject masking, color grading and screen recording without an account (6.4k) | 1 | Sep 2 | Sep 2 |
| OpenShot/openshot-onnx | The export utility that turns YOLO, EfficientSAM and Cutie into ONNX files OpenCV can run on your machine (MIT code, upstream weight terms apply) | 1 | Sep 2 | Sep 2 |
| Deno2026/comfyui-deno-custom-nodes | 8-step MiniMax H3 sampling, a visual bbox prompt builder for Ideogram 4, and a text-encoder unload node for tight VRAM (159) | 1 | Sep 2 | Sep 2 |
| Kosinkadink/ComfyUI-VideoHelperSuite | Video load and combine nodes that most of these workflows depend on for audio and frame handling | 1 | Sep 2 | Sep 2 |
| Riemann-Dynamics/Matrix-Game-3.5 | Walk a camera through a generated 720p scene and have the scene still be there when you turn around (149) | 1 | Sep 1 | Sep 1 |
| MiniMax-AI/MiniMax-H3 | The model this week's entire accessory economy attaches to (7.6k) | 1 | Aug 31 | Aug 31 |
| dntpi/ComfyUI-Hand-Tie-Clips | Chains H3 generations into one long clip, and at 4 stars it is one person's project, not a trend (4) | 1 | Aug 31 | Aug 31 |
| apple/ml-stable-diffusion | The conversion toolchain that puts an image model on an iPhone (18k) | 1 | Aug 30 | Aug 30 |
| microsoft/renderformer | Neural global illumination, MIT, runs on Metal at 8GB (971) | 1 | Aug 30 | Aug 30 |
| 0xShug0/audio.cpp | Portable C++ audio generation, added ControlFoley in v0.7 (2.1k) | 1 | Aug 29 | Aug 29 |
| Stability-AI/stable-audio-3 | The runtime that pulls those CPU engines on first use (704) | 1 | Aug 29 | Aug 29 |
| google-ai-edge/LiteRT | The runtime behind the three on-device image models (3.3k stars) | 1 | Aug 28 | Aug 28 |
| amap-cvlab/ABot-World | Real-time interactive world generation on one desktop GPU (2.5k stars) | 1 | Aug 28 | Aug 28 |
| ace-step/ACE-Step | Open music generation, the model behind the new Mac builds (4.8k stars) | 1 | Aug 27 | Aug 27 |
| ModelTC/Minimax-H3-Turbo | The distillation project that made H3 practical (318 stars) | 1 | Aug 27 | Aug 27 |
| xiaomi-research/controlfoley | Video-to-audio with reference-timbre control (147 stars) | 1 | Aug 27 | Aug 27 |
| mvp-ai-lab/RAVEN | Streaming video generation research (93 stars) | 1 | Aug 27 | Aug 27 |
Method: tools are parsed from the “Open and local” section of each daily briefing. Star totals are verified against the GitHub API at scan time; the Days column counts distinct briefing days a repo appeared, not stars.
A leaderboard tells you what to install. The Workflow Index tells you what to type once it is installed, and where it will break.