AllDSH
中文

The state of DSH plugins, September 2026

An ecosystem snapshot for September 2026: what grew, which categories matured, how verification adoption is trending and what still needs fixing.

Written by AllDSH Editorial · Editorial team

Maintains the verification levels, categories and install specs in this directory.

DeepSeek Harness has been in developer preview long enough for the plugin ecosystem around it to develop a shape. This is a snapshot of that shape, based on the listings tracked in this directory and their repository signals.

Growth is real, and uneven

The plugin population keeps expanding, and the distribution is steep. A small number of repositories attract most of the attention, while a long tail of genuinely useful single-purpose plugins receives almost none. That distribution is normal, and it is exactly why discovery matters more than ranking: the thirtieth search plugin may be a better fit for your setup than the first.

Four categories matured

Four areas now have plugins that behave like infrastructure rather than experiments:

  • Vision. Structured evidence output, tiled OCR for long captures, and pixel tooling for regression checks.
  • Context inspection. Composition breakdowns and compaction event logs turned context tuning into measurement.
  • Memory. Approval gates, bounded retrieval and audit surfaces replaced opaque accumulation.
  • Search. Zero-key providers made browsing a default rather than a paid upgrade.

Three categories are still volatile

Interface plugins remain the most fragile, because they hook rendering paths that change most between preview releases. Agent orchestration plugins are maturing fast but still surprise people with unbounded loops. Model routing plugins carry the quiet risk of changing answer quality without saying so.

Verification adoption is climbing

More listings now declare a dshTarget and a license than did a quarter ago, and more repositories carry the dsh-plugin topic, which is the mechanism that makes any of this discoverable. The remaining gap is install specification accuracy: a meaningful share of listings still show a command that does not match the published package name.

What still needs fixing

Three problems worth naming, because directories can help with all of them.

  1. Compatibility declarations lag releases. A plugin that works but does not say so is treated as broken.
  2. Install specs drift from reality. A wrong command wastes the trust a listing earned.
  3. Security posture is undocumented. Permission surfaces are usually discoverable from source but rarely stated, which pushes every user through the same review.

What is coming

Expect the interface churn to continue while the runtime is in preview, more convergence on structured evidence formats for tool output, and the first serious attempts at cost and routing transparency in the model category. The directory will keep tracking all three.

Sources & references

The technical claims on this page rest on the primary documents below. Each link is followed so it can be checked directly.

  1. [1]deepseek-ai/deepseek-harness — GitHubUpstream repository for DeepSeek Harness, the Cordis runtime and the plugin loading model.
  2. [2]@deepseek-ai/dsh on npm — npmPublished harness package, including the release tags our dshTarget field tracks.
  3. [3]dsh-plugin GitHub topic — GitHubThe discovery mechanism used to find plugins listed in this directory.
  4. [4]About semantic versioning — npm DocsThe versioning convention behind the compatibility and dshTarget guidance.
  5. [5]Keep a Changelog 1.1.0 — Keep a ChangelogThe changelog convention recommended for plugins that want maintainable release notes.
  6. [6]OWASP Top 10 — OWASP FoundationRisk categories referenced by the security review checklist on each listing.

All links last verified 2026-09-11

ESC

Type to search the index. Built at deploy time by Pagefind.