Plugins

Automatic context compression for DeepSeek Harness: compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.

Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section

DeepSeek Harness plugin for bounded, provenance-linked context steady state with recoverable raw history

Surgical rewriting of the model-visible conversation history of a DSH session (surface replacement); edit reply and reasoning chain separately. 上下文手术刀：强制改写会话的模型可见历史，回复与思考链分开编辑。

Anthropic Model Context Protocol (MCP) client bridge plugin for DeepSeek Harness (dsh).

Native dsh (DeepSeek Harness) Cordis plugin adapter for vision-translation: grounds images into <vision-context> via the Python CLI (PROTOCOL v1). Spawns cli.py, never re-implements core logic.

DeepSeek Harness (DSH) plugin — inject context when user input or model output hits configured keywords, with toggleable/configurable rules and model-editable memory.

A friendly status and context-pressure companion for DeepSeek Harness Web

Codex-style code and file selection for DeepSeek Harness Web: workspace file tree + file viewer; selecting code or a whole file adds it to the message as context automatically

DeepSeek Harness bundle that exposes Model Context Protocol (MCP) servers — stdio, streamable HTTP and legacy SSE — as native Harness tools, with a settings UI, live status, auto-reconnect, and backup/restore via local files or WebDAV.

Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement

Minimal-anchored agent preset: request #1 keeps the real bash + str_replace_editor pair with auto-injected context stripped, then promotion unlocks the full Standard catalog and posts a one-shot background-jobs notice against sleep-polling habits.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

Injects allowlisted GitHub Actions and GitLab CI run metadata into agent context without reading logs, credentials, or provider APIs.

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

A `search` tool that learns to pick between fast and thorough search strategies using a contextual bandit (Thompson sampling), improving from real usage instead of a fixed heuristic.

Chemical safety intelligence through the hosted MSDS Chain MCP endpoint: 23 tools for compatibility and mixing order, GHS hazards, PPE, storage, waste disposal, exposure limits, transport classification, multi-region regulatory compliance, SDS lookup and version diffs, and signed audit reports, each answer citing the supplier SDS and revision date it is grounded in.

DSH ↔ agentmemory session-memory bridge: mirrors session lifecycle into a local agentmemory daemon (REST), exposes memory_recall / memory_remember tools, and injects a per-session memory context window via agent/pre-step.

A markdown notes manager for DSH: full **MD notes manager** and **MD notes editor**, quickly capture conversations into notes, maintain notes by **syncing to Git repositories**, and **bring notes into the conversation context**.

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and oversized content through the official ctx.compaction seam.