jackwener/DeepseekHarness-Android: 免 ROOT 免 Termux，一个 APK 在安卓手机上跑 DeepSeek Harness。引擎内嵌 App 进程 · 读屏操作 App · 改系统设置 · 定时/条件自动化 · 可选 Shizuku
免 ROOT 免 Termux，一个 APK 在安卓手机上跑 DeepSeek Harness。引擎内嵌 App 进程 · 读屏操作 App · 改系统设置 · 定时/条件自动化 · 可选 Shizuku
Repositories
jackwener/DSH-Android: 免 ROOT 免 Termux，一个 APK 在安卓手机上跑 DeepSeek Harness。引擎内嵌 App 进程 · 读屏操作 App · 改系统设置 · 定时/条件自动化 · 可选 Shizuku
免 ROOT 免 Termux，一个 APK 在安卓手机上跑 DeepSeek Harness。引擎内嵌 App 进程 · 读屏操作 App · 改系统设置 · 定时/条件自动化 · 可选 Shizuku
oxnw/ai-phone: A SIP phone daemon with local speech and language models on Apple Silicon.
A SIP phone daemon with local speech and language models on Apple Silicon.
GDG-UAM/ml-contest-materials: Official repository of materials for the GDG on Campus UAM's 1st Machine Learning Contest 🏆
Official repository of materials for the GDG on Campus UAM's 1st Machine Learning Contest 🏆
stmorgenstern/diff-soup: a general-purpose, differentiable scientific software for simulating IBVP and BVP PD(A)Es + ODEs + DAEs
a general-purpose, differentiable scientific software for simulating IBVP and BVP PD(A)Es + ODEs + DAEs
davemessew/AgentFlux: Agentic AI platform for visual workflows and autonomous agents. Run it with Docker on your own computer or server.
Agentic AI platform for visual workflows and autonomous agents. Run it with Docker on your own computer or server.
gkjuwon-tech/ouroboros: Runs multi-B LLMs on a 2GB laptop MX150 (beating RTX 4060 in token decode) & hits 23.35 TFLOPS on A100 — zero-dependency single-file Rust GPU compiler
Runs multi-B LLMs on a 2GB laptop MX150 (beating RTX 4060 in token decode) & hits 23.35 TFLOPS on A100 — zero-dependency single-file Rust GPU compiler
TonyD365/Inkhue: A black-and-white print that carries its own color. Print photos and documents on any B/W printer; scan them, and the color comes back.
A black-and-white print that carries its own color. Print photos and documents on any B/W printer; scan them, and the color comes back.
anhao/ai-pose-gallery-zh: 中文版 AI 姿势参考图库 · 1439 组 / 2878 张图片 / 完整汉化 · 零依赖静态画廊
中文版 AI 姿势参考图库 · 1439 组 / 2878 张图片 / 完整汉化 · 零依赖静态画廊
Plateaulk/Awesome-Industrial-Anomaly-Image-Generation: A curated list of industrial anomaly image generation with diffusion, flow, autoregressive, and hybrid models at CCF A/B venues (2024–2026).
A curated list of industrial anomaly image generation with diffusion, flow, autoregressive, and hybrid models at CCF A/B venues (2024–2026).
DiffuSpace/Clover-35B-A3B-Preview: A 35B diffusion language model.
A 35B diffusion language model.
st1vms/AModel: Advanced machine learning and data-driven football (soccer) prediction engine designed to forecast match outcomes, analyze team performance, and process sports data seamlessly through automated setup and execution pipelines.
Advanced machine learning and data-driven football (soccer) prediction engine designed to forecast match outcomes, analyze team performance, and process sports data seamlessly thro...
VikingAtKhan/mls-network-plugin-rpocket-team: AI anticheat for Minecraft servers: neural networks catch KillAura, aim assist, triggerbot and reach. Paper, Spigot, Folia 1.16.5–1.21.
AI anticheat for Minecraft servers: neural networks catch KillAura, aim assist, triggerbot and reach. Paper, Spigot, Folia 1.16.5–1.21.
modelflare-ai/AnyModelBot: 🤖 Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. Reach them in the app, WeChat or Feishu; they remember you, work in the background, run commands and use your computer. Pay per use.
🤖 Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through ...
didi/helixharness: HelixHarness 提供完整的 AI Coding 工程化基础能力，还支持不同企业和团队结合自身的业务知识、工程规范和研发流程，持续构建和演进属于自己的专属 Harness
HelixHarness 提供完整的 AI Coding 工程化基础能力，还支持不同企业和团队结合自身的业务知识、工程规范和研发流程，持续构建和演进属于自己的专属 Harness
yu20000505/prompt-forge: 一句话生成生图提示词：五种风格 + 角色设定 + 七类细分标签，可微调撤回、本地保存；纯本地、零运行时依赖，桌面版开箱即用。
一句话生成生图提示词：五种风格 + 角色设定 + 七类细分标签，可微调撤回、本地保存；纯本地、零运行时依赖，桌面版开箱即用。
patch-gg/anymove: Motion capture for any creature from one AI video: two cameras in one frame, a DINOv2 joint reader, the rig fitted in both views, a GLB out.
Motion capture for any creature from one AI video: two cameras in one frame, a DINOv2 joint reader, the rig fitted in both views, a GLB out.
emma-learns4349/PE-MALWARE-ANALYSER: A machine learning-based static analysis tool that examines Windows PE files (.exe/.dll) to to predict whether a file is malicious/benign.
A machine learning-based static analysis tool that examines Windows PE files (.exe/.dll) to to predict whether a file is malicious/benign.
scaleresearch/tt-rl: Reinforcement learning on Tenstorrent hardware: DQN, PPO and SAC trained natively on TT-NN
Reinforcement learning on Tenstorrent hardware: DQN, PPO and SAC trained natively on TT-NN
blakeandersonw/ai-app-playbook: How to build useful, profitable apps in 2026. Clone it and point your coding agent at AGENTS.md.
How to build useful, profitable apps in 2026. Clone it and point your coding agent at AGENTS.md.
eioyuou/StateSV: StateSV: deep state-space learning for somatic structural variant detection from long reads
StateSV: deep state-space learning for somatic structural variant detection from long reads
martinkeith700/ruyiJS: A new-generation, minimalist browser purpose-built for AI-driven automation. The authentic Firefox JavaScript engine and networking stack, with no window and no renderer — made for web scraping, JS reverse engineering, data collection, and getting past bot checks.
A new-generation, minimalist browser purpose-built for AI-driven automation. The authentic Firefox JavaScript engine and networking stack, with no window and no renderer — made for...
mirzayasirabdullahbaig07/Inside-the-Game: Multi-agent match intelligence built on synthetic football event data (no real Premier League data used). Built for the Inside the Game: Developer Hackathon.
Multi-agent match intelligence built on synthetic football event data (no real Premier League data used). Built for the Inside the Game: Developer Hackathon.
guxiaofengu-ops/long-horizon-orchestrator: Durable, model-free waiting and official Codex wakeups for long inference and training loops.
Durable, model-free waiting and official Codex wakeups for long inference and training loops.