Repositories die in de afgelopen 365 dagen zijn aangemaakt en minstens 50 sterren hebben, gerangschikt op gemiddeld aantal sterren per dag sinds ze zijn aangemaakt. Dit zijn projecten die nu aanslaan, nog voordat we er eigen meetgeschiedenis van hebben.
Claude Code Monitor : Monitor & audit every action Claude Code takes on your computer.
让完全不懂技术的人拥有一台真正每天在干活的专属 AI agent ｜ Open-source consulting playbook: ship self-hosted AI agents that non-technical users actually use
Self-hosted threat intelligence platform — feed aggregation, AI triage, MITRE ATT&CK coverage, and Sentinel-integrated detection engineering. Runs standalone or fully Azure-integrated.
Reusable Codex + Claude Code skill and plugin implementing Anthropic's AI-Native SDLC: Plan → Design → Build → Test → Deploy → Maintain, with human approval gates at every handoff.
Local voice cloning + SRT-driven web presentations. Two installable Agent skills: script → voice → motion.
CLI for your personal muse.ai AI agent: chat, side chats, feed, goals, ideas, and sessions from the terminal. No browser needed.
Warm, expressive React components with considered motion. MIT licensed shadcn registry and Fumadocs documentation.
Automated User-Agent database for 100+ browsers on 100+ operating systems. Updated every 5 minutes via GitHub Actions. Weighted by real-world popularity, grouped by OS and browser, with a cumulative ALL/ folder of unique agents.
a lightning-fast, privacy-first, and fully open-source alternative to obsidian
Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.
Fast singing-voice acoustic model: harmonic + noise excitation refined into a mel by a 1-step rectified flow (bundled NHVSing vocoder). Multi-speaker + style control; ONNX/OpenUTAU export.
PythonGeen licentie gevondenAangemaakt Bijgewerkt 2 weken geleden
Myna Recorder — a Windows macro recorder you can read and edit. Image anchors, an auto clicker, an AI assistant that writes macros, Agent mode (computer use, for short jobs) and a screen watchdog.
A true cross platform text expander with a sync engine across all your devices. Available, for Linux, macOS, Windows, iOS, and Android.
559 K パラメータの日本語 TTS を ESP32-S3 で実時間合成。漢字かな交じり文の形態素解析・アクセント推定まで端末内で走る（M5Stack CoreS3 実機で確認）。推論は依存ゼロの C99、ブラウザ demo あり。arXiv:2608.21378 sanoTTS の日本語 clean-room 再実装。⚠️ コードは MIT ですが、配布モデルの重みは MIT ではありません（LICENSE-MODEL.md。出力に用途制限が伝播します）
Dramake：面向 Codex、Claude Code、WorkBuddy 的文字转 AI 短剧 Skill；串起剧本、分镜、Wan 3/Seedance/MiniMax H3、配音、剪辑与质检，适配抖音、红果短剧和横竖屏。
Open-source platform for deploying and running functions behind your own Infra.
JavaGeen licentie gevondenAangemaakt Bijgewerkt 3 weken geleden
Cross-platform, fully-offline Vietnamese/English text-to-speech desktop workstation powered by VieNeu-TTS v3 Turbo (ONNX/CUDA, Voice Cloning, EPUB Audiobooks, PySide6/QML)
PythonGeen licentie gevondenAangemaakt Bijgewerkt 5 dagen geleden
Turn a GitHub repository or Hugging Face model into a finished vertical reel: video, cover art and per-platform copy.
PythonGeen licentie gevondenAangemaakt Bijgewerkt 4 weken geleden
Efficient Stable Diffusion Fine-Tuning Framework 2026: Lightweight Config-Driven Pipeline
The 2026 VRAM-Smart Fine-Tuning Suite for SDXL and ANIMA on 12GB GPUs
Ultimate Flux1-LoRA Training Toolkit 2026: Smart Simplicity for AI Creators
HTMLGeen licentie gevondenAangemaakt Bijgewerkt 4 dagen geleden
Automated LoRA Training Docker Builds for Alibaba Cloud 2026
Timeline director for the MiniMax H3 video model in ComfyUI — shots, camera moves and audio cues compiled into the structured prompt H3 reads. Independent project, inspired by LTXDirector.
Manage upto 1000 agents using automations and workflows