{"name":"Loadbay","description":"Catalog of harnesses for AI agents, across domains.","repo":"https://github.com/alessandrorodi/loadbay","count":58,"domains":{"trading":"Trading","coding":"Coding & DevOps","browser":"Browser & computer","productivity":"Productivity","data":"Data & search","social":"Social & comms","health":"Health","science":"Research & science","gaming":"Gaming","media":"Voice & media","robotics":"Robotics"},"traits":{"mcp":"Exposes an MCP server","keys":"Needs API keys / auth","sandbox":"Runs sandboxed","guard":"Guardrails / limits"},"harnesses":[{"slug":"minimax-mcp","name":"MiniMax-MCP","author":"MiniMax-AI","domain":"media","integrations":["MiniMax"],"language":"Python","license":"MIT","stars":1500,"traits":["mcp","oss","keys"],"summary":"MiniMax's official MCP server — give an agent text-to-speech, voice cloning, and image and video generation.","repo":"https://github.com/MiniMax-AI/MiniMax-MCP","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/minimax-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"bolna","name":"Bolna","author":"bolna-ai","domain":"media","integrations":["Voice"],"language":"Python","license":"MIT","stars":675,"traits":["oss","keys"],"summary":"An open framework for building conversational voice AI agents, including telephony.","repo":"https://github.com/bolna-ai/bolna","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/bolna","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"generative-media-skills","name":"Generative-Media-Skills","author":"SamurAIGPT","domain":"media","integrations":["Media"],"language":"Shell","license":"MIT","stars":3600,"traits":["oss","keys"],"summary":"Multimodal generative-media skills (image, video, audio) you mount into a coding or agent runtime.","repo":"https://github.com/SamurAIGPT/Generative-Media-Skills","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/generative-media-skills","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"pipecat","name":"pipecat","author":"pipecat-ai","domain":"media","integrations":["ElevenLabs","Deepgram"],"language":"Python","license":"Other","stars":12870,"traits":["oss","keys"],"summary":"Open-source framework for building realtime voice and multimodal conversational AI agents with pluggable STT, LLM, and TTS.","repo":"https://github.com/pipecat-ai/pipecat","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/pipecat","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"livekit-agents","name":"agents","author":"livekit","domain":"media","integrations":["LiveKit","ElevenLabs"],"language":"Python","license":"Apache-2.0","stars":11019,"traits":["oss","keys"],"summary":"Framework for building realtime voice and video AI agents that join LiveKit rooms with streaming STT, LLM, and TTS pipelines.","repo":"https://github.com/livekit/agents","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/livekit-agents","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"audiocraft","name":"audiocraft","author":"facebookresearch","domain":"media","integrations":["MusicGen"],"language":"Python","license":"MIT","stars":23380,"traits":["oss"],"summary":"Meta's library for audio generation featuring the MusicGen music model and the EnCodec audio tokenizer.","repo":"https://github.com/facebookresearch/audiocraft","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/audiocraft","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"diffusers","name":"diffusers","author":"huggingface","domain":"media","integrations":["Stable Diffusion","Flux"],"language":"Python","license":"Apache-2.0","stars":33879,"traits":["oss"],"summary":"Hugging Face library of state-of-the-art diffusion models and pipelines for image, video, and audio generation in PyTorch.","repo":"https://github.com/huggingface/diffusers","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/diffusers","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"elevenlabs-python","name":"elevenlabs-python","author":"elevenlabs","domain":"media","integrations":["ElevenLabs"],"language":"Python","license":"MIT","stars":3006,"traits":["oss","keys"],"summary":"Official Python SDK for the ElevenLabs API, giving agents text-to-speech, voice cloning, and audio generation.","repo":"https://github.com/elevenlabs/elevenlabs-python","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/elevenlabs-python","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"whisper-streaming","name":"whisper_streaming","author":"ufal","domain":"media","integrations":["Whisper"],"language":"Python","license":"MIT","stars":3640,"traits":["oss"],"summary":"Realtime streaming wrapper around Whisper for long-form, low-latency speech-to-text transcription and translation.","repo":"https://github.com/ufal/whisper_streaming","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/whisper-streaming","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"spotify-mcp","name":"spotify-mcp","author":"varunneal","domain":"media","integrations":["Spotify"],"language":"Python","license":"MIT","stars":605,"traits":["mcp","oss","keys"],"summary":"MCP server that connects an LLM to Spotify to control playback, search the catalog, and manage queues and playlists.","repo":"https://github.com/varunneal/spotify-mcp","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/spotify-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"youtube-transcript-mcp","name":"mcp-server-youtube-transcript","author":"kimtaeyoon83","domain":"media","integrations":["YouTube"],"language":"TypeScript","license":"MIT","stars":563,"traits":["mcp","oss"],"summary":"MCP server that fetches YouTube video transcripts so an AI assistant can read and summarize video content.","repo":"https://github.com/kimtaeyoon83/mcp-server-youtube-transcript","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/youtube-transcript-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"blender-mcp","name":"blender-mcp","author":"ahujasid","domain":"media","integrations":["Blender"],"language":"Python","license":"MIT","stars":22876,"traits":["mcp","oss"],"summary":"MCP server that connects Claude to Blender for prompt-driven 3D modeling, scene creation, and rendering.","repo":"https://github.com/ahujasid/blender-mcp","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/blender-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"comfyui","name":"ComfyUI","author":"comfyanonymous","domain":"media","integrations":["Stable Diffusion","Flux"],"language":"Python","license":"GPL-3.0","stars":117384,"traits":["oss"],"summary":"Modular node-graph diffusion GUI, API, and backend for image and video generation that agents can drive via workflows.","repo":"https://github.com/comfyanonymous/ComfyUI","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/comfyui","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"fooocus","name":"Fooocus","author":"lllyasviel","domain":"media","integrations":["Stable Diffusion"],"language":"Python","license":"GPL-3.0","stars":50314,"traits":["oss"],"summary":"Streamlined Stable Diffusion image generator focused on prompting with minimal configuration.","repo":"https://github.com/lllyasviel/Fooocus","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/fooocus","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"invokeai","name":"InvokeAI","author":"invoke-ai","domain":"media","integrations":["Stable Diffusion"],"language":"TypeScript","license":"Apache-2.0","stars":27456,"traits":["oss"],"summary":"Creative engine and WebUI for Stable Diffusion with a node workflow system and REST API for generating visual media.","repo":"https://github.com/invoke-ai/InvokeAI","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/invokeai","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"stable-diffusion-webui","name":"stable-diffusion-webui","author":"AUTOMATIC1111","domain":"media","integrations":["Stable Diffusion"],"language":"Python","license":"AGPL-3.0","stars":163770,"traits":["oss"],"summary":"The most widely used Stable Diffusion web UI with extensions and an API endpoint agents can call for text-to-image.","repo":"https://github.com/AUTOMATIC1111/stable-diffusion-webui","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/stable-diffusion-webui","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"animatediff","name":"AnimateDiff","author":"guoyww","domain":"media","integrations":["Stable Diffusion"],"language":"Python","license":"Apache-2.0","stars":12144,"traits":["oss"],"summary":"Official implementation that animates personalized text-to-image diffusion models into short videos.","repo":"https://github.com/guoyww/AnimateDiff","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/animatediff","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"hunyuanvideo","name":"HunyuanVideo","author":"Tencent-Hunyuan","domain":"media","integrations":["HunyuanVideo"],"language":"Python","license":"Other","stars":12217,"traits":["oss"],"summary":"Tencent framework and open weights for large-scale text-to-video generation.","repo":"https://github.com/Tencent-Hunyuan/HunyuanVideo","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/hunyuanvideo","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"wan2-1","name":"Wan2.1","author":"Wan-Video","domain":"media","integrations":["Wan"],"language":"Python","license":"Apache-2.0","stars":16272,"traits":["oss"],"summary":"Open large-scale video generative models from Alibaba supporting text-to-video and image-to-video synthesis.","repo":"https://github.com/Wan-Video/Wan2.1","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/wan2-1","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"cogvideo","name":"CogVideo","author":"zai-org","domain":"media","integrations":["CogVideoX"],"language":"Python","license":"Apache-2.0","stars":12794,"traits":["oss"],"summary":"Text-to-video and image-to-video generation models including CogVideoX with open weights and inference code.","repo":"https://github.com/zai-org/CogVideo","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/cogvideo","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"mochi","name":"mochi","author":"genmoai","domain":"media","integrations":["Mochi"],"language":"Python","license":"Apache-2.0","stars":3670,"traits":["oss"],"summary":"Open text-to-video generation model from Genmo with code and weights for high-fidelity motion synthesis.","repo":"https://github.com/genmoai/mochi","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/mochi","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"riffusion-hobby","name":"riffusion-hobby","author":"riffusion","domain":"media","integrations":["Riffusion"],"language":"Python","license":"MIT","stars":3898,"traits":["oss"],"summary":"Real-time music generation using Stable Diffusion applied to audio spectrogram images.","repo":"https://github.com/riffusion/riffusion-hobby","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/riffusion-hobby","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"coqui-tts","name":"TTS","author":"coqui-ai","domain":"media","integrations":["XTTS"],"language":"Python","license":"Other","stars":45573,"traits":["oss"],"summary":"Deep-learning text-to-speech and voice-cloning toolkit with many pretrained multilingual models.","repo":"https://github.com/coqui-ai/TTS","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/coqui-tts","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"f5-tts","name":"F5-TTS","author":"SWivid","domain":"media","integrations":["F5-TTS"],"language":"Python","license":"MIT","stars":14771,"traits":["oss"],"summary":"Flow-matching text-to-speech model for fast, fluent zero-shot voice cloning from a short reference clip.","repo":"https://github.com/SWivid/F5-TTS","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/f5-tts","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"openvoice","name":"OpenVoice","author":"myshell-ai","domain":"media","integrations":["OpenVoice"],"language":"Python","license":"MIT","stars":36726,"traits":["oss"],"summary":"Instant voice-cloning audio model that copies tone color and controls style across languages from one reference clip.","repo":"https://github.com/myshell-ai/OpenVoice","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/openvoice","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"bark","name":"bark","author":"suno-ai","domain":"media","integrations":["Bark"],"language":"Python","license":"MIT","stars":39159,"traits":["oss"],"summary":"Text-prompted generative audio model that produces speech, music, sound effects, and nonverbal sounds from text.","repo":"https://github.com/suno-ai/bark","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/bark","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"chattts","name":"ChatTTS","author":"2noise","domain":"media","integrations":["ChatTTS"],"language":"Python","license":"AGPL-3.0","stars":39469,"traits":["oss"],"summary":"Generative speech model optimized for natural conversational dialogue in English and Chinese.","repo":"https://github.com/2noise/ChatTTS","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/chattts","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"kokoro","name":"kokoro","author":"hexgrad","domain":"media","integrations":["Kokoro"],"language":"Python","license":"Apache-2.0","stars":7520,"traits":["oss"],"summary":"Lightweight 82M-parameter text-to-speech model delivering high-quality multilingual voices with low compute.","repo":"https://github.com/hexgrad/kokoro","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/kokoro","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"sadtalker","name":"SadTalker","author":"OpenTalker","domain":"media","integrations":["SadTalker"],"language":"Python","license":"Other","stars":13902,"traits":["oss"],"summary":"Generates stylized talking-head videos from a single portrait image and an audio clip.","repo":"https://github.com/OpenTalker/SadTalker","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/sadtalker","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"wav2lip","name":"Wav2Lip","author":"Rudrabha","domain":"media","integrations":["Wav2Lip"],"language":"Python","license":"Unlicensed","stars":13046,"traits":["oss"],"summary":"Lip-sync model that accurately matches a face video to any target speech audio in the wild.","repo":"https://github.com/Rudrabha/Wav2Lip","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/wav2lip","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"screenshot-to-code","name":"screenshot-to-code","author":"abi","domain":"media","integrations":["Claude","GPT"],"language":"Python","license":"MIT","stars":72941,"traits":["oss","keys"],"summary":"Drops in a screenshot and converts it to clean HTML, Tailwind, React, or Vue code using vision models.","repo":"https://github.com/abi/screenshot-to-code","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/screenshot-to-code","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"draw-a-ui","name":"draw-a-ui","author":"SawyerHood","domain":"media","integrations":["GPT"],"language":"TypeScript","license":"MIT","stars":13601,"traits":["oss","keys"],"summary":"Draw a low-fidelity mockup on a canvas and generate working HTML from it with a vision model.","repo":"https://github.com/SawyerHood/draw-a-ui","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/draw-a-ui","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"hunyuan3d-2","name":"Hunyuan3D-2","author":"Tencent-Hunyuan","domain":"media","integrations":["Hunyuan3D"],"language":"Python","license":"Other","stars":13988,"traits":["oss"],"summary":"High-resolution image-to-3D and text-to-3D asset generation using large-scale Hunyuan3D diffusion models.","repo":"https://github.com/Tencent-Hunyuan/Hunyuan3D-2","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/hunyuan3d-2","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"whisper","name":"Whisper","author":"openai","domain":"media","integrations":["PyTorch","ffmpeg","HuggingFace"],"language":"Python","license":"MIT","stars":102900,"traits":["oss"],"summary":"OpenAI robust multilingual speech-to-text model and the de-facto open standard for transcription and translation.","repo":"https://github.com/openai/whisper","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/whisper","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"whisper-cpp","name":"whisper.cpp","author":"ggml-org","domain":"media","integrations":["ggml","CUDA","Core ML"],"language":"C++","license":"MIT","stars":50800,"traits":["oss","sandbox"],"summary":"High-performance C/C++ port of Whisper for fast local and on-device speech-to-text with no Python runtime.","repo":"https://github.com/ggml-org/whisper.cpp","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/whisper-cpp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"whisperx","name":"WhisperX","author":"m-bain","domain":"media","integrations":["faster-whisper","pyannote","PyTorch"],"language":"Python","license":"BSD-2-Clause","stars":22500,"traits":["oss"],"summary":"Whisper with word-level timestamps, voice activity detection, and speaker diarization for aligned, speaker-attributed transcripts.","repo":"https://github.com/m-bain/whisperX","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/whisperx","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"flux","name":"FLUX.1","author":"black-forest-labs","domain":"media","integrations":["PyTorch","ComfyUI","diffusers"],"language":"Python","license":"Apache-2.0","stars":25600,"traits":["oss","keys"],"summary":"Official inference for the FLUX.1 family, the leading open-weight text-to-image diffusion models.","repo":"https://github.com/black-forest-labs/flux","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/flux","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"stability-generative-models","name":"Stability generative-models","author":"Stability-AI","domain":"media","integrations":["PyTorch","diffusers","ComfyUI"],"language":"Python","license":"MIT","stars":27200,"traits":["oss"],"summary":"Stability AI official repo for SDXL, SD 2.x, and Stable Video Diffusion, the canonical Stable Diffusion model family.","repo":"https://github.com/Stability-AI/generative-models","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/stability-generative-models","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"fish-speech","name":"Fish Speech","author":"fishaudio","domain":"media","integrations":["PyTorch","HuggingFace","Gradio"],"language":"Python","license":"Apache-2.0","stars":30800,"traits":["oss"],"summary":"State-of-the-art open multilingual text-to-speech with voice cloning and low-latency synthesis.","repo":"https://github.com/fishaudio/fish-speech","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/fish-speech","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"chatterbox","name":"Chatterbox","author":"resemble-ai","domain":"media","integrations":["PyTorch","HuggingFace"],"language":"Python","license":"MIT","stars":25100,"traits":["oss"],"summary":"Resemble AI open SOTA text-to-speech with expressive zero-shot voice cloning and emotion control.","repo":"https://github.com/resemble-ai/chatterbox","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/chatterbox","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"csm","name":"CSM","author":"SesameAILabs","domain":"media","integrations":["PyTorch","HuggingFace"],"language":"Python","license":"Apache-2.0","stars":14600,"traits":["oss"],"summary":"Sesame open conversational speech generation model for natural, context-aware spoken dialogue and voice agents.","repo":"https://github.com/SesameAILabs/csm","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/csm","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"liveportrait","name":"LivePortrait","author":"KlingAIResearch","domain":"media","integrations":["PyTorch","ComfyUI","ONNX"],"language":"Python","license":"MIT","stars":18600,"traits":["oss"],"summary":"Efficient portrait animation that drives a single source image with video, audio, or image-derived motion.","repo":"https://github.com/KlingAIResearch/LivePortrait","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/liveportrait","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"open-sora","name":"Open-Sora","author":"hpcaitech","domain":"media","integrations":["PyTorch","HuggingFace","Colossal-AI"],"language":"Python","license":"Apache-2.0","stars":29100,"traits":["oss"],"summary":"Open-source text-to-video generation framework aiming to democratize Sora-style video with full training and inference code.","repo":"https://github.com/hpcaitech/Open-Sora","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/open-sora","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"real-esrgan","name":"Real-ESRGAN","author":"xinntao","domain":"media","integrations":["PyTorch","ComfyUI","NCNN"],"language":"Python","license":"BSD-3-Clause","stars":35800,"traits":["oss"],"summary":"Practical algorithms for general image and video super-resolution and restoration; the standard open upscaler.","repo":"https://github.com/xinntao/Real-ESRGAN","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/real-esrgan","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"facefusion","name":"FaceFusion","author":"facefusion","domain":"media","integrations":["ONNX Runtime","ffmpeg","Gradio"],"language":"Python","license":"Other","stars":28800,"traits":["oss","sandbox"],"summary":"Open face-swapping and face-manipulation platform with CLI and headless modes for automated media pipelines.","repo":"https://github.com/facefusion/facefusion","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/facefusion","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"elevenlabs-mcp","name":"ElevenLabs MCP","author":"elevenlabs","domain":"media","integrations":["MCP","Claude Desktop","Cursor"],"language":"Python","license":"MIT","stars":1100,"traits":["oss","mcp","keys"],"summary":"Official ElevenLabs MCP server exposing text-to-speech, voice cloning, speech-to-text, and audio tools to MCP clients.","repo":"https://github.com/elevenlabs/elevenlabs-mcp","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/elevenlabs-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"openmontage","name":"OpenMontage","author":"calesthio","domain":"media","integrations":["Claude Code","ElevenLabs","Stable Diffusion","FFmpeg","Remotion"],"language":null,"license":"AGPL-3.0","stars":23115,"traits":["oss","keys"],"summary":"An agentic video production system with 12 pipelines, 52 tools, and 500+ agent skills — an agent handles research, scripting, asset generation, clip retrieval, timeline editing, and final rendering from a plain-language prompt.","repo":"https://github.com/calesthio/OpenMontage","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/openmontage","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"video-use","name":"video-use","author":"browser-use","domain":"media","integrations":["Claude Code","Codex","Hermes","ElevenLabs","ffmpeg","HyperFrames","Remotion","Manim"],"language":null,"license":"MIT","stars":10438,"traits":["oss","keys"],"summary":"An open-source video editing harness for coding agents: drop raw footage in a folder, chat with Claude Code or any shell-capable agent, and get a finished video back. Agents drive ffmpeg pipelines to cut filler words, auto color grade, burn subtitles, and spawn parallel sub-agents for animation overlays.","repo":"https://github.com/browser-use/video-use","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/video-use","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"claude-video","name":"claude-video","author":"bradautomates","domain":"media","integrations":["Claude Code","YouTube","ffmpeg","Whisper"],"language":null,"license":"MIT","stars":8000,"traits":["oss","keys"],"summary":"Claude Code slash command (/watch) that downloads any video, extracts frames, transcribes audio, and feeds the full context to Claude so the agent can reason about video content.","repo":"https://github.com/bradautomates/claude-video","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/claude-video","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"pollinations","name":"Pollinations","author":"pollinations","domain":"media","integrations":["Claude","MCP clients","Stable Diffusion","Flux"],"language":null,"license":"MIT","stars":4855,"traits":["oss","mcp"],"summary":"An open-source generative AI platform with a built-in MCP server that unifies text, image, video, audio, 3D, and embedding generation under a single API endpoint, powering 500+ community projects without requiring API keys.","repo":"https://github.com/pollinations/pollinations","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/pollinations","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"orkas-videostudio","name":"Orkas-VideoStudio","author":"Orkas-AI","domain":"media","integrations":["Claude Code","Codex","Cursor","ffmpeg","whisper.cpp"],"language":null,"license":"MIT","stars":520,"traits":["oss","mcp"],"summary":"An MCP server that turns any coding agent into a video production studio: the agent describes a video in natural language and the server renders the timeline and output file using ffmpeg. Exposes tools for composing clips, subtitles, TTS narration, and motion graphics.","repo":"https://github.com/Orkas-AI/Orkas-VideoStudio","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/orkas-videostudio","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"comfyui-mcp","name":"comfyui-mcp","author":"artokun","domain":"media","integrations":["ComfyUI","Claude","ChatGPT","Gemini","Ollama","Stable Diffusion","FLUX"],"language":null,"license":"MIT","stars":593,"traits":["oss","mcp"],"summary":"MCP server giving AI agents 178 tools to control ComfyUI for local image, video, and audio generation. Agents can author and run workflows, generate media assets, and edit the live ComfyUI graph in natural language; works with Claude, ChatGPT, Gemini, and offline Ollama.","repo":"https://github.com/artokun/comfyui-mcp","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/comfyui-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"funasr","name":"FunASR","author":"modelscope","domain":"media","integrations":["LangChain","AutoGen","Claude","Cursor","OpenAI-compatible API"],"language":null,"license":"MIT","stars":19889,"traits":["oss","mcp"],"summary":"An open-source speech recognition toolkit with an MCP server that lets AI agents transcribe audio, detect voice activity, identify speakers, and recognize emotions. Provides an OpenAI-compatible local API for seamless integration with agent frameworks like LangChain and AutoGen.","repo":"https://github.com/modelscope/FunASR","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/funasr","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"kinocut","name":"kinocut","author":"KyaniteLabs","domain":"media","integrations":["FFmpeg","Claude Code","Cursor","Hyperframes"],"language":null,"license":"Apache-2.0","stars":116,"traits":["oss","mcp","guard"],"summary":"A guardrailed local video editing MCP server for AI agents, exposing 196 tools for trimming, merging, captioning, audio normalization, and social platform repurposing. Includes preflight validation and quality checkpoints so agents cannot publish media without human inspection.","repo":"https://github.com/KyaniteLabs/kinocut","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/kinocut","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"ableton-mcp","name":"ableton-mcp","author":"ahujasid","domain":"media","integrations":["Ableton Live","Claude Desktop","Claude"],"language":null,"license":"MIT","stars":2913,"traits":["oss","mcp"],"summary":"MCP server connecting Ableton Live to Claude and other AI agents for prompt-driven music production, track creation, clip arrangement, and real-time session manipulation.","repo":"https://github.com/ahujasid/ableton-mcp","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/ableton-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"voicestudio","name":"VoiceStudio","author":"debpalash","domain":"media","integrations":["Claude Code","Cursor","MCP clients","OpenAI audio API"],"language":null,"license":"AGPL-3.0","stars":14064,"traits":["oss","mcp"],"summary":"A fully-local, open-source ElevenLabs alternative that exposes an MCP server for voice synthesis and transcription so coding agents can trigger speech generation, video dubbing, and dictation without cloud accounts. Provides an OpenAI-compatible audio API at localhost and installable agent skills for Claude Code and Cursor.","repo":"https://github.com/debpalash/VoiceStudio","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/voicestudio","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"hyperframes","name":"HyperFrames","author":"heygen-com","domain":"media","integrations":["Puppeteer","ffmpeg","GSAP","MCP"],"language":null,"license":"Apache-2.0","stars":44900,"traits":["oss","mcp"],"summary":"Open-source framework for turning HTML, CSS, and seekable animations into deterministic MP4 videos, built for AI agents. Includes MCP tooling for motion and composition workflows.","repo":"https://github.com/heygen-com/hyperframes","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/hyperframes","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"voicebox","name":"voicebox","author":"jamiepine","domain":"media","integrations":["Claude Code","Cursor","Windsurf","Whisper","Local TTS engines"],"language":null,"license":"MIT","stars":52765,"traits":["oss","mcp"],"summary":"A local-first voice I/O studio that exposes TTS, STT, and voice cloning to AI agents via an MCP server. Agents connect via MCP to call tools like voicebox.speak, voicebox.transcribe, and voicebox.list_profiles, with all audio processing running on-device for full privacy. Supports 7 TTS engines, Whisper-based dictation, and per-client voice binding for Claude Code, Cursor, and Windsurf.","repo":"https://github.com/jamiepine/voicebox","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/voicebox","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}}]}