Official news, first rumor reports and substantive progress. Each entry keeps the information published at that time.
- DeepSeek Harness shows Creator Mode demos and bilingual prompt packs
DeepSeek Harness published Creator Mode demos and seven Chinese/English prompt sets that show building plugins in natural language. Harness is still in developer preview; some plugins were refined over multiple turns, so a single prompt may not reproduce the demo.
- DeepSeek opens its in-house search engine to developers with new Search and Fetch APIs
DeepSeek's API change log says it is opening up the in-house search engine that already powers search in its web app and API. DeepSeek describes DeepSeek Search as an AI-native, multilingual engine indexing hundreds of billions of web pages and handling hundreds of millions of searches a day, and says it filters SEO spam, GEO manipulation and low-quality AI-generated content. The Search API (POST /v1/tools/search) returns up to 50 structured results per query with optional page content and supports operators such as site:, lang:, after: and before:. A companion Fetch API (POST /v1/tools/fetch) returns a single web page as Markdown. Both use the standard DeepSeek API key and are aimed at agents and RAG applications. DeepSeek lists both at $0.75 per 1,000 successful requests, and says Search and Fetch calls made server-side when using its API in DeepSeek Harness, Claude Code or Codex are free for now but will be billed per call from 00:00 Beijing time on November 1, 2026.
- DeepSeek and Huawei release open-source Ascend AI chip tools
The Decoder reports DeepSeek and Huawei built open-source programming tools for Huawei's Ascend AI chips, centred on TileLang for simpler kernel programming.
- DeepSeek updates its open-source repos, adding Huawei Ascend support
DeepSeek pushed updates across most of its open-source kernel and communication libraries on GitHub, adding Huawei Ascend support through new DeepGEMM-Ascend and DeepEP-Ascend repositories, alongside updates to FlashMLA, DeepGEMM, DeepEP, DeepSelect and TileKernels, plus a new DeepJIT library for xPU kernel JIT compilation, per its GitHub repos.