99 Model Provider Plugins for DeepSeek Harness

The provider-neutral LLM seam. Adapters register on ctx.llm; only two ship in-box (llm-deepseek, llm-pi-ai). Swapping a model means writing one adapter — the loop and compaction never change.

What DeepSeek Harness defines at this extension point

Official slot

packages/llm

Extension kind

seam

ctx keys (2)

ctx.llmctx.tokenMeter

Official built-ins

DeepSeek ships 2 implementations herellm-deepseek, llm-pi-ai

Gap

largehow much of this seam the official taxonomy grades as still open

Audience

developer

Artifact kind

cordis-plugin

Seams

1

Every field above is read from the DeepSeek Harness (DSH) source tree — deepseek-ai/deepseek-harness — not from our own guesswork about what these projects do. Same data as a live filter: browse this category in the full plugin list.

99 Model Provider Plugins indexed here

D

DSH AUX

DoloresCaritasAngelus

Auxiliary model system for DeepSeek Harness: unified aux-LLM routing (per-task model, timeout, concurrency, failure cooldown, main-model fallback) + vision_analyze / web_extract / compress_text tools, settings page, and session image lifecycle cleanup.

Not checked0

D

Dsh Sisyphus Presets

hnlg-coder

DeepSeek Harness agent presets: Sisyphus orchestrator (6 expert subagent lanes) + Sisyphus Oracle read-only consultant. Ported from oh-my-openagent workflow.

Not checked0

D

Dsh Reasoning Efforts

liujihaodeku

DeepSeek Harness plugin: configure reasoningEfforts for external llm-pi-ai providers

Not checked0