DeepSeek Research, Models, Infrastructure, and Agent Systems
DeepSeek models and API releases, the open DeepInfer inference engine, and the DeepSeek Harness agent runtime, checked against primary sources.
Models, API, and inference 3
DeepInfer Benchmarks: 2× Serving Throughput, 0.59 s TTFT and Hopper Support from Community PRs
We read 191 DeepInfer PRs. Turning off EPLB doubled serving throughput, a prefix cache cut TTFT from 8.9 s to 0.59 s, and Hopper, AMD and...
DeepInfer: DeepSeek's Open-Source Inference Engine for V4.1 Flash, Explained
DeepInfer is the engine behind DeepSeek's production serving, now open source. See what it runs, the hardware it needs, what was left out...
DeepSeek V4.1 Flash 1017: What Changed, Benchmarks, Pricing and the New Search API
DeepSeek V4.1 Flash 1017 replaces the model behind deepseek-flash at the same price. See the benchmark gains, peak pricing, Search/Fetch ...
DeepSeek Harness 6
DeepSeek Super-agent: A Router and Worker Multi-Agent Architecture
How DeepSeek's Super-agent design splits a resident Router from parallel Workers, routes events by thread, and what its synthetic experim...
How DeepSeek Harness PTC Mode Actually Works
DeepSeek Harness PTC Mode explained from source: how the generated Code Mode SDK and run_code execute multi-tool programs, plus token and...
DeepSeek Harness Modes Explained
Compare DeepSeek Harness Standard, PTC, Minimal, and Creator modes by tools, execution model, security boundary, and best use case.
DeepSeek Harness Creator Mode: How It Works and Its Risks
DeepSeek Harness Creator Mode explained from source: runtime inspection, dynamic plugins, custom agent presets, process lifetime, and she...
DeepSeek Harness vs Pi Agent: Plugin Runtime or Minimal Coding Harness?
DeepSeek Harness and Pi Agent compared across architecture, extensions, MCP, sandboxing, sessions, deployment, and best-fit engineering w...
DeepSeek Harness Architecture: How It Works and Whether to Adopt It
How DeepSeek Harness uses Cordis plugins for models, tools, sessions, approvals, and sandboxes—and what its developer-preview status mean...
About this page
DeepSeek work splits into three tracks, covered separately here: models and the API developers call, the DeepInfer inference engine, and the DeepSeek Harness agent runtime. We use primary sources (repositories, release notes, model cards, API docs) and only log changes that affect capability, interfaces, deployment, or benchmarks.