TapNow launched CreativeOS 2.0 on October 17, centering on an Agent that writes and executes code to organize, generate, and modify visual content. Code2Video also underpins Cinemap and Monta, while tests by PingWest produced a roughly 40-second Chinese product explainer and an 18-second, three-camera 3D blocking rehearsal.
NetEase Zhichi upgraded its Emperor Crab enterprise AI Agent platform with the smart badge, the Wandian knowledge engine, and Agent Team, according to 36Kr and Zhidx. The smart badge brings field information into AI systems, while Wandian organizes documents, email, tickets, CRM data and conversations; Agent Team coordinates specialized agents across complex tasks. NetEase Zhichi said the upgrades connect information, knowledge and execution, but the reports provide no independent performance benchmarks.
What problem it solves
Developers need abstractions that can accommodate increasingly agentic LLMs without limiting their reasoning and tool-use abilities through rigid prompts or opinionated orchestration. They also need a way to turn agent components into multi-tenant, multi-session applications with supporting infrastructure.
Key features
Composable agent building blocks — Compose agents from a…
Optimizing a GPU kernel or completing a set of formal proofs often requires repeated trial and error: try a different implementation, run an evaluation, and keep iterating in whichever direction proves effective. When giving a model more test-time compute, the most direct approach is to let more agents try simultaneously; if the task only needs one best result, the value of the other attempts lies…
What problem it solves
OpenPencil lets users describe UI in natural language and see it appear on an infinite canvas, then modify existing designs by selecting elements and chatting. It also lets multiple AI agents work on different sections of complex pages in parallel while keeping `.op` files human-readable, Git-friendly and diffable.
Key features
Prompt-to-canvas generation — Describe a UI in …
What problem it solves
Developers need a coding agent that can fit into different workflows without requiring separate processes for each interface or model provider. They also need access to agentic features, automation, and shared sessions while retaining control over model and provider selection.
Key features
Agentic workflows — The agent includes Auto-Memory, Auto-Skills, SubAgents, Agent Team…
What problem it solves
Teams often need several agents with distinct personalities, models, computers, and connected apps rather than one assistant in a single interface. These agents must also work with existing local CLI sessions, keep local data under user control, and request approval before risky actions.
Key features
Bring your own agent engines — Run bots through Claude, Codex, or Grok CLIs…