API
< Back to situation

[REVISION HISTORY]

DeepSeek expands agent frameworks and multimodal models

30 recorded revisions of this situation.

What changed

2026-09-15 02:31 UTC → 2026-09-30 02:05 UTC · added removed

DeepSeek has expanded its ecosystem through the release of the DeepSeek Harness (DSH), an open-source, MIT-licensed agentic development environment built on the Cordis meta-framework. DSH utilizes a modular, plugin-based architecture that allows developers to swap models, tools, and file systems without modifying core code. It features Chain of Thought (CoT) tracking via append-only logs, enabling users to inspect or replay reasoning processes through a Trajectory view. The company has also transitioned its flagship DeepSeek-V4-Pro (build 0813) from preview to general availability. This 1.6-trillion-parameter Mixture-of-Experts model has shown improved performance in software engineering and cybersecurity benchmarks. To support local deployment, GEEKOM demonstrated a four-node AI cluster using A9 Mega Mini PCs to run DeepSeek V4 Flash locally via USB4. DeepSeek’s multimodal capabilities were extended by the release of DeepSeek-V4-Flash-Vision-Exp. Subsequently, FlashLabs released an experimental, uncensored GGUF quantized version, ‘DeepSeek-V4-Flash-Vision-Uncensored’, designed for security research. In September 2026, DeepSeek released V4.1-Flash, a 552-billion-parameter multimodal Mixture-of-Experts model optimized for coding, agentic tasks, and cost efficiency. The model activates only 8 billion parameters for input and 16 billion for output, reportedly reducing KV-cache size to approximately one-quarter of the previous V4 Flash generation. V4.1-Flash achieved a score of 90.6 on Terminal-Bench 2.1, outperforming competitors like OpenAI’s GPT-5.6 Sol. The release triggered market volatility, contributing to a decline in shares for Samsung Electronics and SK Hynix as investors reassessed AI hardware requirements. Some developers have raised concerns regarding the rapid routing of V4 Pro requests to the new Flash model, citing potential risks to stability and research reproducibility. Furthering its agentic capabilities, DeepSeek released DeepSeek Harness v0.2 in preview. This update introduces desktop installation packages for macOS and Windows, transitioning the tool from terminal-based deployment to a more accessible application format.

Versions

  1. 2026-09-30 02:05 UTC DeepSeek expands agent frameworks and multimodal models
  2. 2026-09-15 02:31 UTC DeepSeek expands agent frameworks and multimodal models
  3. 2026-09-09 08:41 UTC DeepSeek expands agent frameworks and multimodal models
  4. 2026-09-08 20:15 UTC DeepSeek expands agent frameworks and multimodal models
  5. 2026-09-03 11:06 UTC DeepSeek expands agent frameworks and multimodal models
  6. 2026-08-25 05:31 UTC DeepSeek expands agent frameworks and multimodal models
  7. 2026-08-22 18:37 UTC DeepSeek expands agent frameworks and multimodal models
  8. 2026-08-21 07:43 UTC DeepSeek expands agent frameworks and local execution tools
  9. 2026-08-20 23:14 UTC DeepSeek expands agent frameworks and local execution tools
  10. 2026-08-20 07:12 UTC Chinese AI firms expand low-cost LLMs and agent frameworks
  11. 2026-08-19 00:30 UTC Chinese AI firms expand low-cost LLMs and agent frameworks
  12. 2026-08-18 02:37 UTC Chinese AI firms expand low-cost LLMs and agent frameworks
  13. 2026-08-18 02:00 UTC Chinese AI firms expand low-cost LLMs and agent frameworks
  14. 2026-08-16 10:10 UTC Chinese AI firms expand low-cost LLMs and agent frameworks
  15. 2026-08-15 09:13 UTC Chinese AI firms expand low-cost LLMs and agent frameworks
  16. 2026-08-14 21:06 UTC Chinese AI firms expand low‑cost LLMs, revenue‑share moves
  17. 2026-08-14 11:41 UTC Chinese AI firms expand low‑cost LLMs, revenue‑share moves
  18. 2026-08-14 05:38 UTC Chinese AI firms expand low‑cost LLMs, revenue‑share moves
  19. 2026-08-13 15:13 UTC Chinese AI firms expand low‑cost LLMs, revenue‑share moves
  20. 2026-08-12 23:47 UTC Chinese AI firms expand low‑cost LLMs, revenue‑share moves
  21. 2026-08-10 07:34 UTC Chinese AI firms expand low‑cost LLMs, revenue‑share moves
  22. 2026-08-10 06:14 UTC Chinese AI firms expand low‑cost LLMs, revenue‑share moves
  23. 2026-08-07 22:09 UTC Chinese AI firms expand low‑cost LLMs, revenue‑share moves
  24. 2026-08-07 06:59 UTC Chinese AI firms expand low‑cost LLMs, DeepSeek hikes price
  25. 2026-08-07 01:47 UTC Chinese AI firms expand low‑cost LLMs, DeepSeek hikes prices
  26. 2026-08-06 16:11 UTC Chinese AI firms expand low‑cost LLMs, DeepSeek hikes prices
  27. 2026-08-05 07:29 UTC Chinese AI firms broaden low‑cost, high‑scale LLMs
  28. 2026-08-05 04:35 UTC Chinese AI firms push cost‑focused open‑source LLMs
  29. 2026-08-04 10:26 UTC Chinese AI firms push cost‑focused open‑source LLMs
  30. 2026-08-03 01:44 UTC Chinese AI firms push cost‑focused open‑source LLMs
  31. 2026-07-27 20:44 UTC Chinese AI firms push cost‑focused open‑source LLMs

Select a version to see what changed compared to the one before it.