Havuz

A Herdr client for any screen. Control terminals, monitor coding agents, and review files and diffs from desktop or mobile.

AI goes multiplayer. A self-hosted workspace for people and machine people. Create, code, and work together across desktop, mobile, and web.

Harness-oriented agent system framework for production-grade LLM agent applications

Private control plane for AI agents

gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 MCP和sill，支持龙虾或任何agent使用٩(๑>◡<๑)

面向 Windows 的 ChatGPT 账号注册、邮箱 OTP、账号管理与支付工作台

Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.

EvoTrace, Claude Code ve Codex oturumlarını inceleyip eğitim, değerlendirme ve doğrulama için yeniden kullanılabilir varlıklara dönüştürür.

Neden yükseliyor · 39 günde 292 yıldız, coding agent oturumlarından eğitim ve değerlendirme varlığı üretme fikrine ilgi olduğunu gösteriyor; ancak bu ilginin nedeni ölçümlerden anlaşılamıyor. Son 28 günde commit ve farklı yazar olmaması, ilginin devam eden geliştirme veya benimsemeyle desteklendiğine dair kanıt sunmuyor.

Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune,

免费开源的 AI 剪辑 / 直播切片工具:长视频、直播回放、播客一键切成爆款竖屏短视频,直发抖音/快手/B站/小红书/视频号——AI 找高光金句、弹幕热度进爆点判断、自动加字幕、横屏转竖屏,本地运行无水印不上传 | Free open-source Opus Clip alter

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache co

Open-source local AI workspace — advancing on-device inference.

A multi-agent research system for the humanities and social sciences.

Claude paints with code: a Claude Code skill for procedural illustration in 83 styles, from ink wash (水墨), watercolour and ukiyo-e to staine

CIT Voice Stuido - Chuyển văn bản tiếng Việt thành giọng nói, chạy hoàn toàn trên máy bạn.

MathCode: A Frontier Mathematical Coding Agent

Grasp helps you manage multiple projects and parallel coding agents in one visual workflow, so humans can understand faster and ship more.

groma.md - Your architecture as OKF Markdown in Git, and one C4 map you can walk. Scanned from source, curated by you and your agents.

AI Agent Lockout Backup Kit A vendor-independent continuity kit for backing up, rotating, and recovering information used by AI agents—witho

让 AI 住在你 MacBook 的刘海里 · 零依赖开箱即用 · 多引擎并行的桌面 AI 伴侣（Swift 6 / SwiftUI / macOS 14+）

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's patter

面向 AI Agent 的高并发、低延迟上下文治理与 Prompt Cache 守护网关 (Tree-sitter AST / Tool Delta / 50%~80% Token 削减)

Task-first AI agent skill library · https://skill.wuch-ai.net

DaC is a dashboard-as-code tool. Build interactive dashboards using YAML and JSX. Built-in semantic layer. Get your agents to build standard

Karpathy's understanding ladder as agent skills: auto-pick text, diagram, interactive HTML, or video storyboard for any explanation. Nothing

A fast, native RSS reader — plus an agent-facing CLI so your AI agent can read, search and triage your feeds from the shell.

Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard,

Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent model/tools, Run Center and Toke

Keep your Mac awake only while AI coding agents are working

Import conversation history from 25+ AI coding agents into DeepSeek Harness as resumable sessions — tool calls, reasoning and results kept i

[ECCV 2026] Official implementation of "HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Model

A tiny macOS app that turns Caps Lock into a physical keep-awake switch for closed-lid MacBook work.

From ticket to reviewed pull request. Free and open-source, on your machine.

Loopcut: an AI agent that works inside Blender. A fork of Blender (GPL).

All-in-one board for DeepSeek Harness: MCP manager + Skills + WorkBuddy experts (attach/switch/detach any time) + tool-usage tailor + three

Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, s

2026 最新 Claude 防封号深度指南：6 大封号原因解析 + 实战防封方案对比 + Claude Code 国内安全使用全攻略 · 持续更新

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protoco

LLM agent 的有界自纠错长期记忆层：把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamic

The online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it

内嵌式 AI Agent 桌面应用——自动识别 AI 回复中的命令和工具调用并在本地执行

Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky

Community-maintained skills for specialized HyperFrames workflows.

Composable mathematics tools for agents

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.

企业级 AI 智能体 Agent 平台，覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测，每个环节都经过深 度设计和工程化打磨。

Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed-memory core now ships inside JuliusBrussee/caveman

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

Claude Code mod: hands off to a fresh conversation when context fills up, keeps the cache warm while you're away, and turns what you teach C

DSH Desktop, DeepSeek Harness runtime’ını masaüstünde çalıştıran ve iPhone ile Android’den uzaktan kontrol etmeyi sağlayan bir uygulamadır.

Neden yükseliyor · 44 günde 285 yıldıza ulaşması, DeepSeek Harness’ı kurulum ve mobil erişimle birlikte daha kolay kullanma vaadinin ilgi gördüğünü düşündürüyor. Ancak yıldızlar benimsemeyi kanıtlamıyor; son 28 günde 3 commit ve 1 farklı yazar, devam eden geliştirme için sınırlı kanıt sunuyor.