Havuz

开源 AI 订阅商品公开报价聚合、分类与价格追踪平台

The open alternative to traditional HMI/SCADA panels — browser-based, self-hosted, OPC-UA. In-browser page editor. Built on FastAPI + React.

Athena RAG Intelligence – AI-powered document intelligence platform with RAG, semantic search, source citations, voice assistant, analytics,

Self-hosted email client for several IMAP mailboxes: conversations, full-text search, rules, contacts, tasks, multi-user and OpenID Connect

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

Self-hosted engine that turns URLs, files and text into media, transcripts, summaries, translations and documents — HomeTube, Studio, MCP, C

Self-hosted AI video, image and audio studio on the Higgsfield and ElevenLabs APIs: MCP server for Claude Code, Codex and ChatGPT, REST API

Speed test tracker for the homelab: live gauge, schedules with random times, history, alerts and an API. Measures with Cloudflare, LibreSpee

Meridian AI for learners: multi-agent procurement audit and RAG document Q&A (FastAPI, LangChain, Gemini, Vertex AI, Cloud Run). Code, READM

Multi-service toolkit for Tavily and Firecrawl signup automation, key validation, and isolated proxy pools.

OpenAI-compatible Web Chat API proxy with GPT, Grok, Gemini account management and Docker self-hosting

Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent

Open-source browser-based CAN bus analyzer. Works with low cost USB hardware.

Open Source Alternative to Lovable, v0, Bolt, Replit, Emergent. 🌟 Star if you like it!

JoyCode API 代理 — 协议翻译成 Anthropic/OpenAI 兼容格式，让 Claude Code 直接调用 JoyCode支持的模型，比如GLM 5.1等

中文互联网内容的个人 AI 稍后读 + 知识库 · Read-later + AI knowledge base for the Chinese internet

Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker co

Self-hosted AI customer-support platform — per-KB RAG on Qdrant, 13 LLM providers, SSE streaming, embeddable chat widget. FastAPI + Vite + S

Local-first image prompt library for generating images, saving prompts, tags, and collections.

デジタル庁のガバメントAI「源内(GENAI)」を完全ローカル(ローカルLLM/OpenAI互換)で動かす非公式プロジェクト。SAML認証(Keycloak)・RAG(Qdrant)・文字起こし(Whisper)・画像生成(SD)・チーム単位ナレッジをローカル完結。

Flatbed-scanner photometric stereo for generating normal, albedo, height, and alpha texture maps.

Local-first cinematic still archive for filmmakers. Search your frames by look, mood, technique or director with SigLIP semantic search; ing

Turn the daily TLDR newsletters into a podcast. Local, deterministic, no LLM.

Self-hosted "guess the intro" music quiz for family game night — plays your own Navidrome library on a cast TV or speaker, phones are the bu

🚀 An industrial-grade AI job application system (BOSS/Liepin/51job). Workflow: Scraping ➡️ SQLite ➡️ LLM Eval ➡️ RPA Delivery. | 🚀 工业级全自动 A

Automated GitHub account registration toolkit — signup, email verification, first repo, TOTP 2FA with recovery codes, and profile completion

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

Run-aware token governance for multi-agent systems.

首款支持 CLI 化操作的微信公众号编辑器 — 让你的Agent直接写出精美推文

Reverse-engineered ChatGPT.com web voice (/realtime/wm + WebRTC + DataChannel). Drive live voice with a free web access_token from your own

One dashboard for all your AI agents — manage teams across Claude Code, Codex, Gemini, Aider, and more. No database required.

A web dashboard that shows your server's port usage as a traffic-light grid. Built for homelabbers who run many Docker Compose stacks and ke

Command-deck proxy ops console — users, nodes, cores & subscription delivery.

Local macOS dashboard for your Hermes Agent skills — auto-syncs SKILL.md files from ~/.hermes, customizable top menu bar (pick your own on f

Self-hosted shopping intelligence platform with native serverless Android app and optional Docker web service.

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable

AI-powered interactive RPG engine with persistent memory, independent NPC minds, creativity-based combat, and a reactive world. Build scen

A self-hosted, private-first LLM companion and memory assistant.

省心订阅：自托管的订阅 / 续费 / 保号管理系统，14 种渠道提醒按时续费 · Self-hosted subscription & renewal manager with reminders over 14 channels (Telegram, WeCom, Feishu

Self-hosted web panel for the SoftEther VPN Server: the complete JSON-RPC management API, live machine monitoring, and a one-command install

Self-hosted, OpenAI-compatible speech server: faster-whisper STT and Piper/Kokoro TTS. A local voice backend for Open WebUI, CLIs, and custo

Turn your Plex library into curated, themed virtual TV channels in Tunarr — a self-hosted web app with a *arr-style UI.

54 production architecture rules for vibe coding with Claude Code & Cursor. Drop-in CLAUDE.md, .cursor/rules, and .claude/skills for FastAPI

Automated Cloudflare WARP IP rotator and proxy server for OpenCode Zen. Eliminates HTTP 429 rate limits, persists usage metrics in SQLite, a

AI that shares your terminal session. Open-source AI terminal where the AI types commands directly into your shell, not just suggests them.

Self-hosted EPUB reading stack: native Android reader (Quire) + FastAPI sync server (opds-sync), backed by calibre-web. No telemetry, no clo

多模态电商智能导购 Agent - 基于 RAG 的购买决策助手（ByteDance AI Challenge 参赛项目）

🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app

Self-hosted Telegram multi-account management with Web UI, CLI, Bot, MCP, Telethon, and Telegram Desktop tdata import.

面向长视频理解与证据分析的 Video Agent 平台，基于 FastAPI、Vue、MySQL、Redis 和 RocketMQ，支持 ASR/OCR 时间轴证据。