From Assistant to Colleague: Building Multi-User Agents with OpenViking's Peer Mode (blog.openviking.ai/post/agen…)

你是否听说过“知识编译”，也就是将一个形态的知识转化为另一个形态的知识，例如：将团队周报转换为月报，将文献调研转换为 LLM Wiki，将工作记录转换为 Skill。OpenViking 提出全新 ov compile 命令，将复杂的知识工程转换为高度可控可理解的“知识编译”过程。github.com/volcengine/OpenVi…

The integration between TanStack and Rspack continues to improve 🚀 Have you tried it yet? We’d love your feedback!

Rslint v0.7 is here🦀 TypeScript-first, ESLint-compatible, and 30% faster than v0.6

🦀 Rspack 2.1 is here! ⚡️ 16% faster builds than 2.0 ⚛️ Rust React Compiler: 7–13× faster than Babel 🎨 Improved built-in CSS 📂 import.meta.glob 🔵 TypeScript 7 RC support 🧩 Source Phase Imports

One skill. Five platforms. Midscene Skills gives Claude Code & Codex eyes + hands across browser, desktop, Android, iOS and HarmonyOS. Same chat-driven prompt. No MCP setup.

🌲Rspack's tree shaking just got smarter 🦀 Two recent optimizations remove more unused code: 1. Inlined booleans can make branch-local dependencies inactive 2. Namespace default re-exports now preserve property-level usage More precise bundles, less dead code

Everyone is building AI agents. Very few are building the infrastructure needed to actually run and train them at scale. Today the veRL team at ByteDance open-sourced Uni-Agent: A unified framework for building, running, and training real-world agents. Why this matters: Most agent frameworks focus on orchestration. Uni-Agent focuses on infrastructure. It unifies: - agent execution - environment interaction - large-scale concurrency - RL training into one reusable stack. That means the same system can scale from: prototype → deployment → RL optimization without rebuilding the stack every time. The project is still early, but the direction is extremely promising for: - coding agents - browser agents - computer-use agents - large-scale agent training Open sourced by the team behind veRL (21k+⭐). Repo: github.com/verl-project/uni-… Would love feedback, contributors, and early adopters. #OpenSource #AI #AIAgents #RL #LLM #ByteDance

🚀 Lance is released! Lance is a native unified multimodal model from ByteDance Intelligent Creation Lab, supporting image/video understanding, generation, and editing in a single framework. With 3B activated parameters, Lance explores multi-task synergy for unified multimodal modeling, covering X2T, X2I, and X2V tasks with strong performance across generation, editing, and understanding benchmarks. Check it out and , give a star: Homepage: lance-project.github.io arXiv: arxiv.org/abs/2605.18678 HuggingFace: huggingface.co/bytedance-res… GitHub: github.com/bytedance/Lance #Lance #MultimodalAI #UnifiedMultimodalModel #ImageGeneration #VideoGeneration #OpenSource

🦀Rstest 0.10.0 released! 🚀 Faster. Leaner. More reliable~ ⚡ worker_threads-based pool 🎯 --changed / --related test runs 💾 Persistent build cache 🧠 Memory-aware worker spawn 🔇 Silent passed test consoles 🔍 Profile test runs with --trace

Get Inside the OpenViking Context Database Architecture blog.openviking.ai/post/open…

Two years building Midscene.js, we made a bet we should've made earlier: UI automation has to move from "reading the DOM" to "looking at the screen." So in our 1.0 release (Dec 2025), we dropped DOM compatibility entirely.

Inside AIO Sandbox (Part 3): Integrating AIO Sandbox with NVIDIA OpenShell medium.com/p/inside-aio-sand…

🦀 Install any of Rstack Skills instantly: ``` npx skills add rstackjs/agent-skills --skill <skill-name> ``` 15+ Skills covering debugging, tracing, upgrading, and analyzing

Rspack 2.0 has landed 🦀 The growth since 1.0 is wild: 📈 100K → 5M weekly downloads ⚡️ ~100% faster builds 📉 devServer: 192 deps → 1 And new stuff hits hard: 🧩 Pure ESM core, modern ESM library output ⚛️ Experimental RSC support ... Lean, Fast, Modern Web Bundling 🚀

Great Share! Introduce our awesome work on Hermes Agent✨ Hermes Agent + OpenViking = a powerful combo for Agent development.🚀Worth a try🙌