DeepSeek Harness is an open-source desktop and web UI agent harness for macOS (Apple silicon) and Windows (64-bit) that frames “everything is a plugin.” It aims to accelerate everyday work (document organization, data analysis, slide and doc drafting), coding (repo exploration, bug fixes, tests), research (fact-finding and citation), and background automation (scripts, batch jobs, scheduled tasks). The interface previews mixed file types (Word, Excel, PDFs, code) and supports conversational refinement of outputs. Built-in and experimental plugins (voice input, terminal, agent loops, subagents) extend functionality; users can install official bundles or add third-party plugins through a plugin manager. DeepSeek is in public preview worldwide and distributed under MIT, with download, GitHub, docs, and community links.
Developer tooling emphasizes rapid plugin creation and deep observability: “Creator mode” can scaffold plugins (example: a floating Pomodoro timer built, installed, and verified), while Scheduled Tasks can create recurring workflows (JSON schedule example for a weekly report at 17:00 Asia/Shanghai). Execution traces and a trajectory/timeline view show tool calls, timing, and runtime context to debug agent behavior. Launch options include npx @deepseek-ai/dsh web or cloning the repository; the project invites developers to explore an evolving, composable plugin ecosystem and contribute via GitHub.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
AstaBrief is an open-source model designed for fast scientific report generation, capable of turning research questions and literature into cited reports. It reduces generation time by nearly three and a half times compared to proprietary models, making it a useful tool for researchers. (allenai.org)
Shrivu Shankar argues that SaaS companies are evolving into 'harnesses,' where core tasks are performed by AI agents rather than humans. This shift transforms organizational structure, with humans overseeing and reviewing AI-driven processes within the company. (blog.sshh.io)
Three AI agents - Meta’s Muse, Anthropic’s Claude, and OpenAI’s GPT - were tested on multilingual research tasks involving U.S. and Iranian data. The experiment focused on how language and context influence agent performance across reasoning, sourcing, and artifact creation. (royapakzad.substack.com)
An open-source project named LDRAW-NOVA allows users to generate Lego models using AI. The repository contains tools, examples, and documentation for creating Lego designs with artificial intelligence. (github.com)
DwarfStar 4 (ds4) is a local inference engine that runs large language and vision models on high-memory Mac, CUDA, and ROCm machines. It supports models like DeepSeek V4 and Qwen3.8, offering CLI, APIs, and persistent cache features for efficient local deployment. (dwarfstar.sh)
Rai is a CPU-only large language model inference engine written entirely in Rust. It aims to provide efficient and pure Rust solutions for LLM deployment without relying on GPUs. (github.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.