Havuz

🔒 Your private AI assistant, 100% local on Windows: chat, vision, documents (RAG), web search, images, videos with sound, voice, code projec

Agent 式的 SillyTavern 角色卡酒馆：高缓存命中，兼容酒馆角色卡与世界书，自带配图和一键朗读，角色形象固定，引导式创作角色卡。An agent-style SillyTavern card player for your own LLM API.

The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, con

A cache-aware attention and forgetting layer for high-frequency everyday AI chat.

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loa

Anything to API (万物皆可2API): put an AI agent, a script, or even yourself behind an OpenAI-compatible API

Find the best AI models you can run

A minimal coding-agent harness built to measure what context management actually costs: constraint survival after compaction (8%→83%), def

Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + ve

Run cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the

非技术产品经理/学生从想法到上线的 AI 产品开发工具包（规则卡 + 三份技术手册 + 操作手册）

NeoHorse, agent iş akışlarında tool use, coding ve yapılandırılmış kararlar için açık ağırlıklı 4B ve 9B modeller sunuyor.

Neden yükseliyor · 23 günde 1.094 yıldıza ulaşmış; son 28 günde 13 commit ve 6 farklı yazar katkısı da projede yakın dönem geliştirme hareketi olduğunu gösteriyor. README'de model yayını ve arXiv teknik raporu duyurulmuş; ancak ilgi ve ekip aktivitesi, modellerin gerçek kullanımını veya bağımsız başarı teyidini tek başına kanıtlamıyor.

21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a

ParseBench - A Document Parsing Benchmark for AI Agents

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, a

Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own mo

The Most Advanced MCP Server for Unity Editor with execute_code, prompts/resources, input simulation, screenshots, and play mode automation.

Automated quality checks that nudge AI coding agents toward better habits

Track the carbon footprint of your Claude Code sessions, in the terminal and the Claude desktop app

DSH插件市场 / DSH Plugin Marketplace: 在 DeepSeek Harness Web GUI 中一键浏览、安装与更新 GitHub topic:dsh-plugin 的全部插件 | browse, install & update all GitHub

An open-source inference engine for AI functions in SQL

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.

Claude skill & plugin: turn Claude (or any LLM) into an MBB-grade management consultant. Case-interview coaching, strategy frameworks, marke

DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook

Local MCP server that lets AI assistants automate Origin/OriginPro for data and image processing.

AI coding agent for Visual Studio 2022/2026 — chat, inline completion, and five autonomous agents that explore, plan, patch, and verify buil

Centrally manage AI-agent skills, tools, context, permissions, and identity across your entire org. Self-hosted, Git-backed and MCP-native.

A collection of AI agent skills and plugins for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contai

墨知 MoRead —— 原生 Android 本地小说阅读器 + AI 伴读（BYOK）：自绘排版引擎、连续听书、SillyTavern 角色卡、向量记忆、防剧透

助力搭建你的数字 AI 员工军团 — 多 Agent 一行命令组网协作。Claude Code / Claude Agent SDK / Codex / Grok Build 4 runtime + 8+ 家 LLM（Anthropic / OpenAI / xAI / Mini

Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code

Autonomous multi-agent framework to optimize scientific software

不只是对话，是持续认识你的 AI。开源 Android AI 伴侣：本地优先，能替你做事。 | Not just chat — an AI that truly knows you. An open-source, local-first Android AI companion

Self-hosted Chess.com alternative: Game Review for your Chess.com & Lichess games, play vs Stockfish or a friend, lessons + opening trainer,

iOS 键盘：在任何聊天 App 里直接出意图、风险与候选回复——复制消息，键盘上见分晓。Swift / SwiftUI，中英双语。An iOS keyboard that drafts replies inside any chat app.

Chat with local and cloud AI

QQ 群通知实时摘要推送：NapCat/OneBot v11 + AI 过滤闲聊、提取通知与待办，推送微信，自带手机待办台 PWA (QQ group digest with AI notice extraction and mobile task board)

ASD-STE100 Simplified Technical English as a plugin for Claude Code, Codex & coding agents — clearer, unambiguous LLM output

开源 Windows 本地 AI 工作台｜OpenAI-compatible + Claude CLI，99 个桌面/Office 工具，可回退文件操作与可视化多 Agent 工作流。

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

Text-to-CAD tools in Elixir with build123d, OpenSCAD, replicad, and smlibpy.

An evolving AI brain for Home Assistant: one shared memory and set of house rules for every voice assistant, habits it learns, and how much

Agent 工坊（Agent Workshop）：给它一个 PRD、一个需求点子、或一个可落地的 Agent 方向，它推导出架构方案、组件选型与代码骨架，直到一个能在真实环境运行的产品。

See and review any Vivado / Zynq / PYNQ project: drill-down Vivado-style diagrams and clock-domain, constraint and overlay checks for AI cod

涛声 TaoSheng：用一部安卓手机全天收音 → 转写 → 认人 → AI 整理成待办与记忆。无需硬件、无需账号，数据只在你手机里。

三菱 PLC 编程与工程助手。 MCP server and AI workbench for Mitsubishi PLC programming with GX Works2. Generate Ladder and Structured Text, edit native

Skills to bootstrap and expand analytics ontologies from schema, dbt, dashboards and docs. Evidence-backed context, user-defined domains and

给 AI 生成代码做安全审阅的终端工具：410 条漏洞清单，20 条本地规则 + 模型逐条判定（带证据核实），看完 diff 再决定要不要写（Rust）

飲食熱量日誌 App。核心思想：讓 LLM 負責辨識品名與份量自動拆項後輸出結構化 JSON，並在後端接上可以成長的資料庫；熱量一律來自可核對的資料並由程式計算，每個數字都查得到出處。設計決策參考食物辨識研究及相關論文，以 Claude Code（Opus 5.5）協作開發。原為

Local, self-hosted agent infrastructure — one endpoint for every AI client (Claude Code, Codex CLI, Gemini CLI, OpenCode). Unified model acc