Plugins

Turns attached files into versioned evidence: `search_documents` builds a private local index (SQLite FTS5 after a startup capability probe, dependency-free JS fallback otherwise) and returns compact evidence blocks carrying an exact coordinate — PDF page, PPTX slide, text/DOCX line range, or quoted XLSX `Sheet!Range` — which `read_document` expands only while the content version still matches. Contiguous CJK runs are indexed as overlapping bigrams and queried as phrases, so word order is preserved; uploaded raster images take the native vision attachment path instead.

Paired experiments and promotion gates for DSH plugins.

DSH memory plugin: global hot memory + on-demand experience library with FTS5 retrieval and WebUI cards

DSH Plugin Hub agent: reports the profile's installed plugin inventory and runtime health to dsh-ai.org, and doubles as the hub's runtime eval probe.

The `debug` tool for DeepSeek Harness — a model-facing Debug Adapter Protocol tool with 28 operations (launch/attach, breakpoints, continue/pause/step, threads/stackTrace/scopes/variables/evaluate, disassembly, memory, modules, output, terminate) over the

Runs one coding prompt across multiple configured models in isolated Git worktrees, streams side-by-side tool traces and results, and commits the candidate the user adopts for later rounds.

Evidence-first multi-model coding comparison workbench for DeepSeek Harness

RAGFlow knowledge-base retrieval plugin for the DeepSeek Harness.

DeepSeek Harness plugin: Windows toast notification with sound when a session requests elevation approval — shows which session, why, and what is being elevated

Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.

Doctrove: versioned library documentation retrieval MCP server for coding agents — catalog lookup, version selection and focus-ranked doc extraction, with zero runtime dependencies and a dsh bundle.

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.

Agent evaluation platform: benchmark YAML, headless run orchestration, trace-based metrics, and run reports