DSH Desktop is an open-source desktop client for DeepSeek Harness, packaging DeepSeek Harness into a local-first desktop application. DSH Desktop supports macOS and Windows, and can be accessed with a single click without requiring a command line...
dsh-TUI is a Claude Code-style terminal interface plugin for DeepSeek Harness, developed by the community and featured on the official DSH WeChat account. The tool offers a pixelated whale top bar, real-time status bar, flow-based thinking expansion, and dual...
Qwen3.8-27B is a new generation of large-scale model open-sourced by Alibaba's Qianwen team. It employs a native multimodal dense architecture with 27 billion parameters, supports 262K native contexts, and can be extended to 1M tokens via YaRN. After quantization, it can be used on consumer-grade graphics cards...
dots3-note preview is the first version of the open-source dots3 series from the Xiaohongshu dots model lab, and it's part of the same series as the perfect-score model from IMO 2026. The model uses a MoE architecture with 280B total parameters/16B activation parameters, and supports...
MiniMax Music 3.0 is MiniMax's next-generation open-weighted music generation model. The model employs a layered architecture of 8B Global LLM and 0.6B Local LLM, combined with Flow Matching + Flow-VAE...
Wigolo is an open-source local search tool that integrates with programming agents such as Claude Code and Cursor via MCP. It requires no API key and allows for local searching, web scraping, full-site crawling, structured data extraction, and more, all at zero cost.
Gemini 3.7 Flash is Google DeepMind's next-generation flagship AI model. Designed specifically for coding and agent workflows, it represents a significant leap forward in benchmarks such as software engineering, web development, and enterprise automation...
GLM-5.3 is the latest open-source foundational large-scale model from Zhipu. Like GLM-5.2, it utilizes the same foundation, significantly enhancing its intelligence ceiling through extreme post-training scaling. GLM-5.3 is currently the most programmable open-source model.
Grok 4.6 is SpaceXAI's latest flagship large-scale model, boasting 1.5T parameters and a 500,000-token context. Its performance in benchmark tests, including encoding and agent performance, approaches that of Claude Fable 5 and GPT-5.6 Sol...
LTX-2.5 is LTX's open-source AI video generation foundation model, featuring 22 parameters with open weights upon release. The model supports native multi-camera generation, 4K HDR and RAW/EXR professional workflows, and can generate audio simultaneously. ...
PixelRAG is an open-source, native visual RAG framework developed by Berkeley's SkyLab/BAIR. Instead of the traditional approach of extracting web pages into plain text for retrieval, the framework uses the browser to render web pages and PDFs into screenshot tiles, fine-tuning them using LoRA...
Grok Bot is an AI Agent system launched by SpaceXAI. It can log into a user's account and operate websites and tools like a real person, performing tasks for the user 24/7 in the cloud. The system supports multiple bots working in parallel, recording...
dots.tts is a 2 billion-parameter fully continuous autoregressive speech synthesis foundation model jointly open-sourced by the Xiaohongshu dots team and the Shanghai Jiao Tong University X-LANCE Lab. The model directly generates 48kHz audio block by block in a continuous latent space...
DeepSeek Harness is an AI agent runtime framework launched by DeepSeek, with the core concept of 'Model + Harness = Agent'. The framework utilizes engineering modules such as context management, tool call orchestration, and execution sandboxing...
Nemotron 3.5 Lightning is an open-source MoE model with 30 parameters from NVIDIA, optimized for multi-agent systems. Compared to similar models, it offers 4x faster output speed and 30% faster agent task completion...
HOMIE is an open-source digital human video generation framework from the Hong Kong University of Science and Technology. It is based on the Wan2.1-T2V-14B backbone network and integrates the Qwen3-VL multimodal large model. The framework can uniformly handle four elements: digital human, product, logo, and text...
PAST-Bench is a benchmark test developed by Mengdi Wang's team at Princeton University to examine the recursive self-improvement capabilities of personal AI agents. PAST-Bench compares task performance under conditions with and without memory to determine...
Shotcut is an open-source video editing software based on FFmpeg. It is completely free, watermark-free, and has no duration limit. The software supports hundreds of audio and video formats for direct editing without importing, and offers multi-track timelines, keyframe animation, and rich features...
Palmier Pro is a native macOS video editor built from scratch in Swift for the AI era. It's open-source and its basic functions are free. The product embeds generative AI directly into the timeline, supporting Seedance, Kling, and more...
GPT-5.6-Cyber is an AI model developed by OpenAI specifically for cybersecurity. It is built on GPT-5.6 Sol and enhanced for specialized tasks such as vulnerability exploitation and privilege escalation. The model is only available to Daybreak Red level audit customers and...
Muse Glimmer is an open-source language model from Meta with 30 billion parameters, deeply optimized for 24/7 local agent workflows. The model utilizes 4-bit quantization technology, allowing it to run on a single GPU with 24GB of VRAM or...
SmartSub is an open-source, one-stop desktop tool for audio and video subtitling. It integrates the entire workflow into a single application, providing offline speech-to-text conversion based on local models such as Whisper, FunASR, and Qwen3-ASR, and supports 2...
Wan-Animate-2 is a new generation of character animation model open-sourced by the Wanxiang team. As a major architectural upgrade to Wan-Animate, it abandons the dependence on explicit pose skeletons and auxiliary pose extraction networks, replacing them with an end-to-end dual-branch architecture...
Grok Imagine Image 2.0 is a new generation image generation and editing model released by SpaceXAI, available in "Quality Mode" on the grok web platform and iOS and Android apps. It's more than just "re-picking an image"...