Stars
dsh-go — DeepSeek Harness 装进口袋：手机本机运行，也能遥控你的电脑。
Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
A 64-bit command-line operating system primarily written in C
Percho: Minimalist desktop GUI for the Pi coding agent — the same engine as the Pi CLI, in a clean visual interface. Multi-session chat, visual tool approvals, and custom themes.
Open-source Grok Bot alternative with a virtual machine that bots can use
Lamp Guide：zen-gate 的 Windows 桌面重构版。统一模型与渠道管理、聚合轮换、Agent 接入、日夜主题，提供完整安装向导。
Termux - a terminal emulator application for Android OS extendible by variety of packages.
OpenMinis — The AI Agent app across platforms. Fully free and open source.
Lightpanda: the headless browser designed for AI and automation
An on-device AI agent for Android that operates apps and the web to get things done for you.
Reverse engineer anything with agents, from app behavior down to native binaries.
短剧工作台 | 无限时长视频的 MiniMax H3 工作流 | ComfyUI 本地短剧与长视频生成插件
DroidDeck brings the SteamOS experience to Android
deepbeepmeep / WanGP
Forked from Wan-Video/Wan2.1A fast AI Video Generator for the GPU Poor. Supports Minimax H3, LTX-2.3/2.5, Wan 2.1/2.2, Qwen Image 1/2, Krea 2, Hunyuan Video, LTX Video and Flux.
GitHub 加速器 | GitHub accelerator —— Windows 本机代理,免插件、免服务器、零账号。内置 GitHub 真实 IP 表绕过 DNS 污染,BoringSSL(Chrome 同款 TLS 指纹)+ 伪装 SNI 直连官方边缘,clone / push / Release / raw / 网页全场景加速,公共镜像链兜底大文件,退出自动还原。GitHub pr…
An IDE for building Android applicatons on Android.
DSH Bilibili video understanding plugin: timestamped frames, local ASR/OCR, and optional independent vision model.
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Run Stable Diffusion on Android Devices with Snapdragon NPU acceleration. Also supports CPU/GPU inference.
2D rigid/soft-body physics engine with simulation data pipeline. Train lightweight world model StateLeWM to power the interactive game Spirit Push.
DSH 插件：每天替你刷一轮 B站，读字幕挑出值得的、写一份日报，值得的 @ 你
10.1 billion tokens per month. 87 free LLM providers. 1,313 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypt…
Living Memory Coordinate-5: five-axis memory architecture for long-running LLM agents. Minimal SQLite + production PostgreSQL/pgvector reference impls, multi-channel recall pipeline, LLM-proposed h…
Agent-native long-term memory that learns after every run. File-native, auditable, and integrated with Pi, Hermes, OpenCode, and OpenClaw.
Write HTML. Render video. Built for agents.