Havuz

One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.

Bilingual English and Mandarin text to speech in C++ and GGUF. Voice design, cloning, direction and experimental voice conversion. Vulkan ba

DeepSeek Harness Web UI plugin for streaming rendering and scroll handling.

30KB Markdown-native WYSIWYG editor for React, built for AI streaming, human editing, huge files, macOS, Web, and agent workflows.

CyberVerse, WebRTC üzerinden ses odaklı AI agent konuşmaları ve isteğe bağlı digital-human video etkileşimi kurmaya yönelik self-hosted bir framework’tür.

Neden yükseliyor · 1685 yıldızın 169 günde toplanması dikkat çekiyor; tek fotoğraftan digital-human ve gerçek zamanlı sesli etkileşim vaadi, çoklu model seçenekleri ve demo videoları ilgi çekici. Ancak yükselişin nedenini doğrulayacak trafik veya benimsenme verisi yok; son 28 gündeki 3 commit ve 2 farklı yazar, mevcut bakım temposunun sınırlı olduğuna işaret ediyor.

Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual i

A performant markdown library for iOS & macOS that supports streaming

Mirror of https://git.getbusbar.dev/GetBusbar/busbar. Read-only; contribute on Forgejo. The execution control plane for AI agents. Govern ev

Ultrafast Qwen3-TTS: sub-50 ms time-to-first-audio at 10 requests per second.

Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistra

Markdown rendering for AI applications: incremental streaming, LaTeX math, GFM, and CJK typography. Shared engine and core, React and Mantin

Real-time decision features without streaming infra. Turn live events into product reflexes — no Kafka, no Flink, no feature store.

ScribeCrate: open-source, self-hosted Whisper speech-to-text server powered by faster-whisper. OpenAI-compatible transcription and English t

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。

Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and gar

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

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

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

ZhuLing — Zero-config AI Agent framework for Java. One YAML to launch Agents on Spring AI + DDD, with MCP tools, full observability and a Re

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

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

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

Create & stream personalized agentic video briefings on any topic.

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

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

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

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

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

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

SpeakCrate: self-hosted text-to-speech API powered by Kokoro. OpenAI-compatible speech endpoint, 50+ voices across 9 languages, streamed aud

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

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

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

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

The agent loop for Python. Your harness, any model.

Routed Media OS for Claude Code — 96 skills + 13 modes + 7 specialist agents covering FFmpeg, OBS, NDI, DeckLink, Dolby Vision, HDR10+, and

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

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

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

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

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

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

Rust AI Agent framework with MCP support, extensible tools, streaming & multi-agent orchestration

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

OpenAI-compatible multilingual TTS server — Chatterbox on vLLM with real-time PCM audio streaming, low time-to-first-byte (~0.7 s), voice cl

AI 流式接收工具包：SSE 分帧、协议适配（OpenAI / Anthropic / 自定义）、消息不可变 patch 与取消生命周期。· Framework-agnostic AI streaming toolkit: SSE framing, protocol adapte