DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

A guide to choosing between iLIKE, full-text search, trigrams, and vector embeddings for your data

LLM inference in C/C++

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

The agent that grows with you

Browser Harness | Self-healing harness that enables LLMs to complete any task.

Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers

Code for 'JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion'

The best-benchmarked open-source AI memory system. And it's free.

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

[ICLR 2026] Taming large-scale few-step training with self-adversarial flows! 👏🏻

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

[CVPR 2026 Poster] One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer

A self-hosted, privacy-first location timeline platform: an open-source alternative to Google Timeline with automatic trip detection, Immich integration, and rich analytics.

Official repository for LTX-Video

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.

Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.

HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation​

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with b…

Wan: Open and Advanced Large-Scale Video Generative Models

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

[CVPR 2026] 🔥🔥 Official Repo of UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

[ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning