Havuz

麦当劳中国 MCP 的命令行控制面：33 个官方 MCP 工具编排成 kubectl 式 CLI（人格测试/配餐/省钱/下单/积分）+ 麦麦派对策划师 + WorkBuddy Skill + 网页 Playground

多模态检索实战：意图识别、Prompt 工程、Qwen LoRA、EmbeddingGemma 2 与 InfoNCE 对比学习。含真实演示、自有数据接入、训练评测及 RAG 检索组件学习指南。

Open-source Arc alternative for macOS: a Chromium browser for developers with Spaces, a dev command bar and a built-in MCP server for coding

An engineering philosophy that treats the agent as a worker: the system prompt is a JD, skills are certifications, model tiers are degrees,

A GPU-rendered, terminal-first workspace: Agent framework, real shells, IDE, Markdown, and multiplayer — one Rust engine.

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

麦当劳积分资产管家：剔假上架 · 性价比排序 · 抽奖参谋

The best way out there for any AI to connect to LabVIEW.

Best Prompt Engineering Tools for 2026 AI Workflow Optimization

Проверяет промпты и файлы инструкций (CLAUDE.md, AGENTS.md, скиллы) по правилам вашей модели: Claude Fable 5.2, Opus 5.5, Sonnet 5.5, Haiku

Agent Execution Partnership AEE is an open-source control plane that ensures every AI agent action is authorized before it runs, observable

Native macOS terminal for running, monitoring, and reviewing parallel Claude Code and Codex sessions.

Cross-platform Claude Code desktop client by hwwn. Multi-workspace, remote mobile access, session branching, BYO LLM. macOS / Windows / Linu

Agentic AI video generator — fully autonomous text-to-video pipeline with free TTS/voice-clone, auto-editing, captions, and 20+ single-task

A low-poly 3D office that shows your AI coding agents' live status — idle agents sneak off to play Minecraft (no tokens used).

Codex session conversation chat export markdown interactive terminal tool.

DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into

An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.

Epistemological database for agent and human efforts, beliefs, and findings.

Simulate AI Personas in Social Feeds with Real-Time Chat Bots 2026

Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, re

Meeting recorder for your Mac with a live AI assistant. On-device transcription, answers from your own docs mid-call. Local-first and open s

Evaluation Metrics for African Languages

A benchmark for evaluating LLM × harness performance.

Field-tested, open-source skills for Hermes Agent.

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

Read-only MCP server for Yandex Metrika (Яндекс Метрика): verifiable reports, period comparisons, time series and exports for Claude, Cursor

Animated, copy-paste UI components for Expo and React Native — free components, CLI and expo-charts

OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

Code review for your own machines and your own agents. Reviews live where the code does — reached over SSH, WSL or your own tailnet. Desktop

Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and a Strict Fidelity co

An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of

Autonomous multi-agent pentest framework — plans, exploits, verifies (proof-required), CVSS-scores and writes client-ready reports. 104/104

Microsoft Foundry Local - Workshop - Build AI apps locally with Foundry Local - RAG, agents, and multi-agent workflows in Python, JS, and C#

Local-first AI knowledge app and Agent Skill with evidence-backed Wiki, an interactive knowledge universe, Viki Q&A, and shareable knowledge

Your agent, on your phone. A native Android app for Hermes Agent, running entirely on-device (Termux).

Give AI agents their own macOS displays. Keep your screen, cursor, and focus.

Kaleta – an open-source CMS for business websites with a visual page builder, a token design system and Claude over MCP

🧬 devtools for agents

Persistent memory plugin for Codex. Obsidian-style knowledge base that survives across sessions

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

A concise Claude reference bundle for developers, covering commands, MCP servers, plugins, tools, workflows, and agent frameworks in one pla

All-in-one Docker/Podman image: hermes-agent + hermes-webui + hermes-dashboard in a single container

🌊 30 free curated AI models (up to 1M context) for Oh My Pi & Pi. Thin by design — model list, relay proxy, tool-call diagnostics — add your

Claude Code / Codex local AI proxy gateway desktop app (Tauri). Anthropic Messages <-> OpenAI-compatible protocol transform, model mapping,

麦门综合门诊：12 项问诊测出你的麦门体质，出具诊断证明书与 Rp. 处方笺（麦当劳 MCP）

深度学习、强化学习和AI Agents的系统学习路线：42 个实验，每个配数学推导笔记、原创插图和从零实现的代码，持续更新中

[ICML 2026] When Drafts Evolve: Speculative Decoding Meets Online Learning