Havuz

Run a 28.9M-parameter TinyLM on ESP32-S3 with an RP2040 OLED display node for fully local embedded AI inference.

MilkyAi at bilibili🥛| Video-to-Notes Email Service with RAG Customer Support & 38K Followers/Users on Bilibili | Python, PostgreSQL, RAG, A

Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself.

tsov (the shape of voice) — hum it, get a song you can keep editing. A local-first, AI-native music workspace: humming → transcription → arr

Open-source, self-hosted LangGraph Agent Server. Production Postgres + Redis. Same SDK. Same Studio. Zero code changes.

Continue unfinished work across coding agents with portable handoff bundles.

A self-healing scraper for hostile sites: broken selectors repair themselves, browser rendering kicks in when needed, and a coherent identit

🎵 将音乐搬进AI终端 · 打造Coding专属智能DJ · 听歌新范式 · 交互式音乐 ｜A retro pixel DJ for Claude Code / Codex CLI / Terminal with Apple Music / QQ Music / Local Mu

Let your AI agent use your passwords and API keys - without ever letting it see them

Run your AI agents on machines you already own, as one private P2P mesh. OpenAI-compatible, sandboxed with Podman, signed reputation, no clo

Self-hosted, private family AI health steward. Multimodal AI structures health data into a person-centric profile with dashboard & AI consul

Let an AI see and operate Windows apps cheaply, without stealing focus or moving your mouse. MCP server for Claude Code.

麦麦点餐参谋：麦当劳 MCP 点餐比价助手。同一顿饭换一种买法能差十几块，真实门店菜单、全部买法与优惠券一起算，一句话给出最省方案。McDonald's MCP ordering advisor: real store menus, every way to buy, cheap

Multi-account switcher for Claude Code and Claude Desktop: claude-swap (cswap) plus a maintained patch series.

把老板蒸馏成 AI Skill — PUA检测(10大厂流派) · 反击教练(三档话术) · 画饼鉴定 · 证据收集 · 劳动法速查 · 翻车模拟(互动文字游戏) · 汇报优化 · 老板心理预测。整活的外壳，认真保护打工人的内核。

Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.

基于麦当劳官方 mcd-mcp-server 的 MCP 客户端与 WorkBuddy 技能：扫描历史订单中仍来得及用餐评价的权益机会，盘点积分兑换，聚合当月活动。

Typed, confidence-aware agent skill routing with TypeSafe Jev.

Discover, grade, follow and star GitHub repos with a local Ollama model.

CLI server for Zotero 7/8/9 — let AI manage your library. 70+ CLI commands for search, import, PDF, BibTeX, notes, and more. Works with Clau

Agent Skills for small-molecule and protein therapeutics: cheminformatics, molecular ML, docking and dynamics, protein design platforms, and

A self-hosted AI agent runtime with WebUI, MCP tools, context governance, and Record & Replay for deterministic execution & evaluation.

A lightweight annotation standard that helps AI agents navigate codebases faster, with fewer file reads and tool calls

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek model

Claude Code token usage and cost dashboard. Cost per prompt, cache misses and usage limits for Claude Code, Codex and GitHub Copilot CLI, re

把链接分享给你的 AI：提取网页、视频与本地媒体中的可追溯材料。 / Share links with your AI: extract traceable material from web pages, videos, and local media.

中国电商 MCP 连接器：8 个平台、155 个已注册工具。开源标准版，含能力矩阵与实际工程验收记录；真实商家联调状态逐项公开。Chinese commerce MCP connectors with documented capabilities and validation

Agentic event-venue operator demo built on MongoDB Atlas. Showcases three-layer memory (long-term, short-term, shared), hybrid retrieval wit

Open-source, model-agnostic AI company research for long-term investors. · 面向长期投资者的开源、模型无关 AI 公司研究系统。

Let Your AI Play Detroit：Become Human

Let AI agents search the Chinese internet via MCP — Taobao, JD, Xiaohongshu, Zhihu, Weibo, Bilibili, ZSXQ, Douban, Dianping, and more.

Multi-Agent Research & Valuation Engine for Long-short A股多Agent投研分析系统 9位AI分析师 → 质量门控 → 多空辩论 → 风控评估 → 最终决策

A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.

Translate arXiv papers into book-quality PDFs with parallel sub-agents. Reads the LaTeX source, so equations and the paper's own numbering s

Benchmark your local LLMs: speed, memory, and quality, in one command. TUI leaderboard for Ollama, LM Studio, llama.cpp, and vLLM.

📊 Browse your AI coding spend in the terminal — OpenCode, Claude Code, Codex & friends

A production-grade reference implementation for LLM agent systems: flow declared as a LangGraph graph, Pydantic AI for typed agents, generat

A pure-Python reachability and skeletonization layer that decides what a coding agent actually sees before a request reaches the API.

English translation of MiroFish (github.com/666ghj/MiroFish) - A concise and universal swarm intelligence engine for predicting everything.

Persistent memory for AI coding agents: automatic capture, explainable recall, knowledge consolidation, privacy controls, and portable offli

Personal portfolio showcasing my projects, skills, and experience as a Fullstack Developer.

A floating, screen-aware Claude Code chat for Windows - it reads your screen to answer, and runs on your own Claude subscription (no API key

麦门开饭 McRogue —— 基于麦当劳中国 MCP 的一日三餐肉鸽（麦当劳程序员创意开发大赛参赛作品）

Pay-per-call APIs and MCP services for AI agents: document OCR, document analysis, media transcription, browser sessions, and agent inboxes.

本地运行的 DOCX/TXT 长文档改写与审阅工具，支持段内分块、多轮流式处理、Diff 审阅与 DOCX 原位回填。

Voice-first desktop assistant for Windows — talk to your PC and it works inside real apps, safely. By VORNEX.

Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw

Online-adaptive multi-agent framework for enterprise API orchestration. Adaptive circuit breakers, SLA-driven routing, hybrid LLM+rule inten

A tiny pixel Claude mascot on your Windows taskbar that shows your Claude plan usage and acts out what Claude Code is doing. No dependencies