Havuz

飞影 feiying — 发个片名自动入库到飞牛/Emby:Telegram 多源发现 + AI 智能匹配 + 缓存流播 + 剧集自动追更,单 Docker 容器

The Feishu UI for DeepSeek Harness — a panel-driven control console: every slash command a button on the ⚙️ control-panel card, in-card app

Kari just a tui for getting media from providers and playing it in your media player with nice to have features.

Driver-based, zero-dependency, fetch-first TypeScript HTTP client. Hooks, retry, redirect security, RFC 9111 cache, RFC 6265 cookies, Idempo

Zero-buffer video player powered by Telegram channels. Streams via MSE with continuous prebuffering — playback never stalls, even on seeks.

🌊 Streamdown - Headless streaming markdown engine for React: block splitting, smooth reveal, per-char fade animation and LLM output preproce

Production-grade Agent Skills for data engineering AI agents: 73 workflows, platform presets, safe backfill/replay, Kafka & Spark reliabilit

Run Tachiyomi/Aniyomi extensions on PC, Mac or Linux — no Android or emulator needed. Manga & anime, streaming, web UI and REST API.

On-device simultaneous interpretation on Apple Silicon — VoxCPM2 on MLX at the core, streaming TTS in ~170 ms, voice clone, any-pair transla

Tiny Rust port of Pi — a ~4 MB statically-linked coding agent CLI for old/low-resource Linux boxes. OpenAI + Anthropic providers, streaming

Hold-to-talk voice input for Pi CLI — Deepgram streaming STT with live transcription, voice commands, and cross-platform hold detection

VoiceTut-TTS is an Egyptian-Arabic text-to-speech system fine-tuned from OmniVoice on ~380 hours of Egyptian podcast speech. It produces nat

Streaming ASR, audio captioning and speech QA over a whisper-style encoder with pluggable LLM backends

Free and open-source music player for Windows, Mac and Linux

🎬 An open-source movie streaming platform.

Self-Hosted Torrent Client & Media Server

Self-hosted media streaming app for discovering, organizing, and watching movies and TV shows in your browser. Integrates with RealDebrid, T

Agent-native streaming infrastructure. The streaming runtime built for non-human broadcasters.

Reformat a live LLM token stream inflight — separate thinking from answer, collapse repetition, normalize. Google Vertex / OpenRouter / meta

OpenAI- and Anthropic-compatible API gateway for Grok CLI with multi-account OAuth pooling, streaming, retries, and model-aware scheduling.

A high-performance modern streaming media web application built for seamless entertainment and content discovery.

Eve Agent V2 Unleashed — local-first autonomous AI coding agent powered by Ollama

Play YouTube videos directly in your terminal with synchronized audio using ASCII rendering or ANSI truecolor.

A modern movie and TV show streaming application built with a clean and responsive user interface. The app allows users to discover media, b

Deploy streaming ASR + TTS on RK3576/RK3588 — 120ms TTS, 52-language ASR, one Docker command

Open-source AI that watches and hears your screen and reacts live as any personality you design — for faceless content, autonomous AI stream

Lucida downloader CLI for tracks, albums and public playlists — fast parallel downloads via Qobuz/Amazon, with a TUI, resume and transcoding

True incremental Markdown-to-ANSI terminal renderer for streaming LLM output. CommonMark/GFM support tested, no full-document buffering. C C

MCP-first AI foundation for TYPO3. Bring AI agents into TYPO3, on your terms.

Self-hosted OpenAI-compatible API proxy for Google Gemini — authenticated via OAuth 2.0 + PKCE, no paid API key required. Built with Bun + H

Stream Over the Air TV, IPTV, Youtube, Twitch and more directly to Discord

Chromium (Chrome/Edge) DevTools panel for debugging SSE / EventSource / NDJSON streaming responses. Inspect, filter, search, and export stre

Framework-agnostic HLS & DASH video player with full UI. Plugin system, screenshot, thumbnails.

A premium native Jellyfin desktop client built with Tauri, React, TypeScript and MPV.

ACP-friendly Node.js SDK for local coding agents: run Codex, Claude Code, Cursor, OpenCode, and Pi with streaming, abort, and session resume

Create & stream personalized agentic video briefings on any topic.

Generative UI for LLMs using Markdoc {% %} tag syntax

FreeTheAI: free AI API and open model marketplace. One OpenAI-compatible endpoint at api.freetheai.org/v1 with free models, paid plans, and

ScribeCrate Live: self-hosted real-time transcription server powered by WhisperLive and faster-whisper. WebSocket transcription and speech-t

A streaming action language for computer-use agents. LLMs emit one JSON action per line; the executor runs each the moment its newline arriv

One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits.

Schema-aware real-time API gateway for ClickHouse. Async ingestion with per-table batching, JWT/JWKS auth, Hasura-style access policies, que

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory

AI-powered stream and recording control for OBS Studio via MCP — 148 tools for scenes, audio mixer, filters, streaming, recording, and strea

A self hosted streaming platform for your own library

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

Supertonic-ZH — fast on-device Mandarin TTS (pure ONNX). Now with streaming synthesis for real-time dialogue (low first-audio latency, barge

Streaming gists for live work, build output, and agent conversations.

Open-source realtime voice AI with adaptive VAD, latency telemetry, interruptible TTS, an inspectable TypeScript WebSocket gateway, and expe

Local-first, extensible AI agent workspace — FastAPI + Next.js + LangGraph, with skills, MCP tools, artifacts, long-term memory, sub-agents,