Apps
Announcements
Television: Persistent workspace for AI agents
Television is a desktop for your AI agent. Instead of interacting with Codex, Claude Code, Hermes, or other a...
Rebrand to Slash Royale Legacy
Slash Royale has been renamed to Slash Royale Legacy, as I am working on a new version for the Slash Royale A...
A little while ago I posted about Orange , a frontend I built for turning ComfyUI workflows into simple tools...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Contribute to jd-opensource/JoyAI-VL-Interaction development by creating an account on GitHub.
OpenVoiceFeatured
Instantly clone any voice from any text to any speech, in any language https://huggingface.co/spaces/myshell-ai/OpenVoice
Demo of ESpeech TTS models
Stores all your tweets nicely claw-able for agents.
Counteracting the Suno artifacts
🎭 AI Avatar / digital human platform — upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self-hosted. Claude · Whisper · Chatterbox · MuseTalk.
Free voice gen, video gen & anti-copyright yt
Contribute to manat0912/MagicQuillV2 development by creating an account on GitHub.
Orpheus-TTS-FastAPIFeatured
Orpheus TTS is an open-source text-to-speech system built on the Llama-3b backbone. Orpheus demonstrates the emergent capabilities of using LLMs for speech synthesis https://github.com/canopyai/Orpheus-TTS
Next-Gen High-Resolution 3D Model Generation
This app lets you upload any picture and turns it into a 3D Gaussian‑splat model that can be viewed or downloaded as a PLY or .splat file. You can adjust settings like seed, steps, and detail level...
[NVIDIA Only] Wan2.2 video Studio (text/image-to-video, restyle, keyframe, talking-character S2V) + LoRA Gym + MOVA joint audio+video. From 12GB VRAM.
Codex-assisted local 2D animation spritesheet generator and scene compositing workspace.
P2PCLAW Agent Benchmark — connect any LLM agent (Claude, GPT, Gemini, Qwen, Kimi, DeepSeek…) and get scored on 10 dimensions + Tribunal IQ. Dashboard runs locally on :8787, leaderboard at p2pclaw.com/app/benchmark.
Python bindings for llama.cpp
Contribute to hectorg2211/jarvis development by creating an account on GitHub.
Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning
We’re on a journey to advance and democratize artificial intelligence through open source and open science.