Stars
🏆 Self Hosted Gen AI desktop app. Free alternative to Higgsfield, OpenArt, Freepik....
DFlash: Block Diffusion for Flash Speculative Decoding
1,324-exercise fitness dataset — animation GIFs, 180×180 thumbnails, muscle-group & equipment data, and step-by-step instructions in 6 languages. The exercise data layer behind the LogPress app.
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automate…
A beautiful, non-destructive, and GPU-accelerated RAW image editor built with performance in mind.
🔥🔥🔥 Open-source Jira, Linear, Monday, and ClickUp alternative. Plane is a modern project management platform to manage tasks, sprints, docs, and triage.
A self-hostable personal AI agent with vector memory, Composio tools, and Telegram.
[CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming
Open source DocuSign alternative. Create, fill, and sign digital documents ✍️
The SMS Gateway for Android™ app enables sending and receiving SMS messages through an API that can be accessed directly on the device or via a cloud server when direct device access is not possible.
Wan: Open and Advanced Large-Scale Video Generative Models
[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.
[ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.
Open source alternative to Resend, Sendgrid, Postmark etc.
[Archived] Legacy Python Kimi CLI, no longer maintained. Please use Kimi Code CLI: https://github.com/MoonshotAI/kimi-code
Soprano: Instant, Ultra-Realistic Text-to-Speech
The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…
Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents
Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI
AI compositing workflow built on Qwen Image Edit 2509 with Fusion LoRA. Import BG and subject, remove background, composite and mask areas (including shadows), then prompt the model to auto-match l…