LocalAGI is a powerful, self-hostable AI Agent platform designed for maximum privacy and flexibility. A complete drop-in replacement for OpenAI's Responses APIs with advanced agentic capabilities. No clouds. Local AI that works on consumer-grade hardware (CPU and GPU).
Radar
New projects people are discovering or following across Pinokio.
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Vāgdhenu — metered Sanskrit/Vedic chant text-to-speech (DiT + BigVGAN). Apache-2.0.
✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL
The definitive SEO + GEO skill for Claude. Full site audits with scored findings, AI search optimization (Google AI Overviews, ChatGPT, Perplexity), schema generation, E-E-A-T assessment, and 20 diagnostic scripts. Three modes: Audit → Plan → Execute.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Dia is a 1.6B parameter text to speech model created by Nari Labs. Dia directly generates highly realistic dialogue from a transcript. You can condition the output on audio, enabling emotion and tone control. The model can also produce nonverbal communications like laughter, coughing, clearing throat, etc. https://github.com/nari-labs/dia
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Contribute to showlab/ShowAnything development by creating an account on GitHub.
Official Pytorch Code of the Paper "FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization"
Pinokio app to install and run sdbds/YuE-for-windows, tuned defaults for a single RTX 4060 Ti 16GB GPU. Uses Torch 2.5.1+cu124 and requirements-uv.txt.
အသံတွေကို Clone လုပ်နိုင်တဲ့ "သာလိကာ Voice Clone" App ပါ။ သတိထားရမှာက ကိုယ်အသံ cone လုပ်မယ့်သူက ကိုယ့်အသံသာဖြစ်ရမယ်။ အကယ်၍ တခြားတစ်ယောက်ရဲ့ အသံဖြစ်မယ်ဆိုရင် မူရင်းအသံပိုင်ရှင်ဆီမှာ ခွင့်ပြုချက် သွားတောင်ပါ။ အသုံးပြုသူသည် တခြားသူအသံကို ယူသုံးပြီး ပြဿနာတစုံတရာဖြစ်ပါက အပြည့်အဝ 100% ယူရမည်။
Convert standard 2D videos into stereoscopic 3D Side-by-Side format for VR viewing using deep learning
Offline audiobook reader for EPUB, PDF, and TXT with local OmniVoice TTS, character voices, and synced highlighting.
