Havuz

让 AI 实时看见你的屏幕：按变化量筛选帧、多帧拼进一张图，静止画面几乎不花 token

MOSS-TTS-Nano, düşük kaynaklı cihazlarda çok dilli konuşma üretimi ve voice cloning için tasarlanmış 100M parametreli bir TTS modelidir.

Neden yükseliyor · 170 günde 4.412 yıldız alması, çok dilli TTS'yi GPU gerektirmeden çalıştırma ve voice cloning özelliklerinin geliştiriciler için çekici olduğunu gösteriyor. Ancak son 28 günde 2 commit ve 1 farklı yazar olması, yıldız ivmesinin güncel geliştirme etkinliğiyle desteklendiğine dair sınırlı kanıt sunuyor.

Open-source LLM gateway in Rust. One endpoint for OpenAI, Anthropic, Gemini and every other vendor. Any SDK, any model, any tool.

Give a face to your voice AI in 5 lines of code. Generate realtime avatar video connected to your voice AI locally

Mynah — self-hosted realtime digital human. One GPU, full admin console, Apache-2.0. 自己服务器上的实时数字人系统

🪐 HelixWorld: real-time interactive audio-visual world model.

Real-time intraday stock scanner for US equities with a browser dashboard you lay out yourself

An open-source team messenger for groups of up to 30, with spaces, threads, files and voice notes. Built with Next.js and PostgreSQL, deploy

Supabase-compatible backend in a single binary — real Postgres with RLS, no Docker. Works with supabase-js unchanged.

台股看盤與交易研究儀表板：盤中雷達、當沖監控、資金熱浪、籌碼分點追蹤、AI 盤後日報、手機推播。Self-hosted Taiwan stock trading dashboard — real-time radar, day-trade signals, sector heat

Self-hosted Google Analytics 4 dashboard with real-time traffic, funnels, retention, Search Console integration, and a built-in MCP server.

Type-safe, real-time backend framework on your own Cloudflare account — Workers, Durable Objects, D1, R2, Queues. Convex-style DX, Vite-firs

Javascript SDK for real-time interactive video generation with Xmax AI

A macOS menu-bar app for voice control of Claude Code and Codex. When a session stops, it calls you, and you answer by voice or on Telegram.

H3 Max Realtime Education, sesli bilim dersini kesintilere yanıt veren ve konuya göre video üreten bir tutoring uygulamasıdır.

Neden yükseliyor · Sesli AI tutoring ile anlık generative video üretimini tek bir gösterilebilir deneyimde birleştirmesi dikkat çekici olabilir; ancak yükselişin gerçek nedeni verilerden doğrulanamıyor. 27 günde 70 yıldız var, fakat son 28 günde yalnızca 1 commit ve 1 farklı yazar bulunduğundan ilgi, geliştirme temposuna dair güçlü kanıt oluşturmuyor.

OpenPocketBaseSDK, Unreal Engine projelerinin PocketBase servislerine C++ ve Blueprint üzerinden bağlanmasını amaçlayan bir SDK'dır.

Neden yükseliyor · 27 günlük yaşında 77 yıldız almış olması erken ilgiye işaret ediyor; ancak bu ilginin kaynağı bilinmiyor ve son 28 günde 7 commit'in tek yazardan gelmesi topluluk katkısının sınırlı olduğunu gösteriyor.

NetEase Cloud Music Together for ChatGPT — an MCP/Bridge project with realtime room events, bidirectional chat, lyrics context, playback & q

Autonomous backend platform. Your coding agent builds it over MCP, Backenly keeps it running: Postgres, REST APIs, auth, storage, realtime,

Self-hosted cloud for BeeCount — one Docker image runs the sync server + web app · multi-device realtime sync · shared ledgers | 蜜蜂记账自建云:一个

Self-hosted native-Rust runtime for real-time voice agents. Own the stack: one binary in your own VPC or air-gapped, no hosted control plane

让 AI 用自己的手机和号码打真实电话：ESP32 蓝牙桥接，中文控制台，豆包 / OpenAI，Prompt、录音总结与主动重连。

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

Conversational-AI framework for Go.

Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and t

The open-source realtime backend you host yourself. Database, live queries, auth, file storage, cron jobs and a dashboard in one binary. Wri

Free, open source, realtime task manager. Issues, boards, sprints, projects and docs that sync instantly. Keyboard-first, self-hostable, wit

The agentic node editor for live visual effects

抖音直播弹幕中台 (Douyin Live Danmaku Hub)：双采集内核（浏览器+CDP / 轻量直连）、多房间并发、WS/SSE/Webhook 三通道分发、可视化控制台、Docker 一键部署

Fix race conditions across Node.js processes: ordered operations, expiring holds, and state that survives a restart, in your SQL database. A

Voice I/O for LLM chat UIs: dictation, read-along and a voice-reactive aura, for any OpenAI-compatible speech engine.

Fix race conditions on one record in Rails: ordered operations, expiring holds, and durable state in your existing SQL database. A SQL-backe

Voice agents that speak your caller's language: listening, turn-taking, barge-in and the voice, in 29 languages. Open source.

A decentralized peer-to-peer web operating system and workspace powered by WebRTC and distributed signaling.

React Native SDK for real-time interactive video generation with Xmax AI

Open, self-hosted runtime for real-time voice agents — a Rust recreation of ChatGPT's Advanced Voice Mode (GPT-Live), model-neutral

Experimental source-available SQLite/libSQL backend for human-and-agent-native workflows, with Studio and scoped MCP access.

Full-stack LiveKit voice agent starter: a Python voice worker, FastAPI token server, and React frontend. Run, deploy, and swap each piece on

Love小家（CoupleSpace）是一个面向情侣的私密实时共同空间：相册、时光轴、悄悄话、纪念日、AI 日记、情书、地图、通话与共同宠物。

🦞 Headless real-time Python voice assistant powered by ElevenLabs, Gemini, Mem0, MCP tools, and local wake-word detection.

Everything the native EventSource API is missing — typed events, auth headers, reconnect, and single-tab coordination.

Multiplayer infrastructure for AI agents

Paced, streaming Piper TTS for real-time voice pipelines - Asterisk AudioSocket, RTP or WebSocket. Optional ElevenLabs with local fallback.

CODEX × WORKBUDDY Token 监控看板 | 本地实时 SSE 看板，监控 AI 会话的 Token 消耗、命中率与活跃会话最新消息 / Local real-time SSE dashboard monitoring AI session token usage

Watch together in sync; Free Chrome extension for watch parties. Synced video playback, live chat & reactions. Watch movies & YouTube with f

Open-source audio-reactive 3D visualizer for musicians, built with Three.js, WebGL, the Web Audio API, and browser-based MP4 export.

Catena exposes any SQLite database as a secure HTTP + WebSocket API in one small Go binary.

Developer documentation for swaram — a real-time Malayalam voice API for building voice agents.

Open-source Hangfire dashboard extension (Blazor Server) with console output, job tags, recurring job admin, search, filters, analytics, and

Self-hosted LAN game platform — 8 turn-based board games (Monopoly, Risk, Battleship, Yahtzee, Life, Checkers, Connect Four, Tic-Tac-Toe) in

Desktop realtime speech translator for routing translated audio between virtual audio devices in calls.