freestylefly/WeChatBridge: 微信聊天记录一键转发到 AI Agent 与 Obsidian 的原生 macOS 工具
微信聊天记录一键转发到 AI Agent 与 Obsidian 的原生 macOS 工具
Repositories
Alex314618-create/JevRev: An LLM + Jev workflow. Boost your vertebrate brain with a spine inside.
An LLM + Jev workflow. Boost your vertebrate brain with a spine inside.
Rizzo-AI-Academy/rizzo-flow: The open, local take on Jev: typed decisions from an LLM, without generating a single token
The open, local take on Jev: typed decisions from an LLM, without generating a single token
Correr-Zhou/PackLab: Offical Implementation of "PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing"
Offical Implementation of "PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing"
davidalmeida90/quant-models: Open-source quantitative finance models in Python: option pricing and Greeks, volatility surfaces, deep hedging, portfolio construction and Monte Carlo. Every model runs on free data, with the full write-up on davidariasfinance.com
Open-source quantitative finance models in Python: option pricing and Greeks, volatility surfaces, deep hedging, portfolio construction and Monte Carlo. Every model runs on free da...
mmastrac/jevenator2: Jevenator 2: Judgement Day - region-scan localisation on a diffusion LLM
Jevenator 2: Judgement Day - region-scan localisation on a diffusion LLM
amitshekhariitbhu/ai-engineer-roadmap: AI Engineer Roadmap - A step-by-step AI Engineering roadmap to become an AI Engineer, with a blog for every topic.
AI Engineer Roadmap - A step-by-step AI Engineering roadmap to become an AI Engineer, with a blog for every topic.
aovestdipaperino/laya-rust: Pure-Rust inference for the Laya non-autoregressive typed-decision model (ModernBERT-large + RL decision head), on candle
Pure-Rust inference for the Laya non-autoregressive typed-decision model (ModernBERT-large + RL decision head), on candle
KuldeepxAI/krea-turbo-kuldeep: Fast Text-to-Image Generation using the Krea-2-Turbo model (12B parameters) powered by the Wan2GP engine and mmgp offloading.
Fast Text-to-Image Generation using the Krea-2-Turbo model (12B parameters) powered by the Wan2GP engine and mmgp offloading.
zai-org/ZCode: Z.ai's coding agent harness. Powerful, intelligent, extensible.
Z.ai's coding agent harness. Powerful, intelligent, extensible.
Inkloom-art/inkloom: Specialised AI models for logo design — a brand-analysis model turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces real lockups and clear-space rules. Early access open.
Specialised AI models for logo design — a brand-analysis model turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces...
Anil-matcha/awesome-agent-apis: 660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) — one YAML file per entry, browsable by capability.
660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) — one YAML file per entry, browsable by capability.
APIMART-12W22W/gpt-image2.5-api-prompt-gallery: gpt image2.5 API prompt gallery (GPT Image 2.5 / gpt-image-2.5 / gptimage2.5 / image2.5 api): 12 tested prompt recipes with example renders, model version, aspect ratio, per-image cost and copy-paste cURL, Python and JavaScript calls.
gpt image2.5 API prompt gallery (GPT Image 2.5 / gpt-image-2.5 / gptimage2.5 / image2.5 api): 12 tested prompt recipes with example renders, model version, aspect ratio, per-image ...
hometrix/SplashMonitor: First native macOS desktop app and menu bar monitor for Inco AI's Splash local inference engine on Apple Silicon
First native macOS desktop app and menu bar monitor for Inco AI's Splash local inference engine on Apple Silicon
KeWang0622/mri-research-skill: A curated, verified knowledge hub for MRI research — physics, acquisition, reconstruction, analysis, quantitative MRI, spectroscopy, and hardware. Install: npx skills add KeWang0622/mri-research-skill
A curated, verified knowledge hub for MRI research — physics, acquisition, reconstruction, analysis, quantitative MRI, spectroscopy, and hardware. Install: npx skills add KeWang062...
NSStudent/JevSwiftSDK: An independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support.
An independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support.
v-modal/awesome-jev-tools: A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.
A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.
ronivaldo/ml-algorithms-learning-lab: A practical, reproducible guide for learning what machine-learning algorithms exist, how their inputs must be represented, how they behave, and how to choose among them under real engineering constraints.
A practical, reproducible guide for learning what machine-learning algorithms exist, how their inputs must be represented, how they behave, and how to choose among them under real ...
Technicalflight/image-prompt-reverse: 把一张图片逆推成生成提示词（Image to Prompt）：中英双语重建提示词 + 风格标签 + 结构化 JSON prompt，零依赖校验脚本 | Forensic image-to-prompt reconstruction. AGPL-3.0 · Commercial use requires license.
把一张图片逆推成生成提示词（Image to Prompt）：中英双语重建提示词 + 风格标签 + 结构化 JSON prompt，零依赖校验脚本 | Forensic image-to-prompt reconstruction. AGPL-3.0 · Commercial use requires license.
mizorewww/laya-mlx: Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
innovatorved/system-design-in-depth: Production-grade System Design Learning Platform - 18 modules, 200 units, deep engineering mechanics
Production-grade System Design Learning Platform - 18 modules, 200 units, deep engineering mechanics
higun2/MPAD: [ECCV2026] Unified Multi-plane Autoregressive Diffusion for 3D Multi-Contrast MRI Synthesis
[ECCV2026] Unified Multi-plane Autoregressive Diffusion for 3D Multi-Contrast MRI Synthesis
Heman10x-NGU/openJev-verdict-2.0: Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
huangbai-AI/post-production-skill: 用于 AI 视频后期特效创作的 Seedance 2.5 Skill，可生成电影级 VFX、创意转场、三维 UI、动态镜头与视觉合成提示词。
用于 AI 视频后期特效创作的 Seedance 2.5 Skill，可生成电影级 VFX、创意转场、三维 UI、动态镜头与视觉合成提示词。