Plugins

Local Git-backed long-term memory for DeepSeek Harness with hybrid CJK/English retrieval, cited context, transactional sync, previews, and rollback.

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

Moves an existing DSH session to another agent preset through a previewable five-section handoff, preserving the source session and either pausing the target for confirmation or continuing immediately.

Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.

View and manage an agent’s tools and skills in a visual menu. Set each capability to Resident, On-demand, or Disabled; agents can find and use on-demand capabilities while reducing context usage.

Browse Claude Code, DSH and Codex session logs by working directory, with per-turn context composition, token usage, compaction markers and cost estimates.

Claude Code-style auto-memory, natively: typed memory files (user/feedback/project/reference) with a MEMORY.md index auto-injected into the system prompt (zero footprint when empty); memory_write/read/list/delete follow Claude Code write rules (dedupe-and-update, absolute dates, cross-links); workspace-scoped and user-scoped layers, cross-process file locking with orphan-lock recovery, plain Markdown on disk, no external services, no embeddings.

MCP Connector for DeepSeek Harness: a specialist MCP marketplace and MCP manager panel for Model Context Protocol data sources. Connect enterprise, financial, legal, patent, research and geospatial data; manage authorization, search tools and troubleshoot connections. Supports OAuth, API keys and HTTP/stdio. Provider permissions and fees apply.

Unified MCP, skill and expert management board for DeepSeek Harness: connection status, tool schemas, enable/disable and reconnect for MCP servers across global and per-project scopes, enable/disable of SKILL.md skills, attach/switch/detach WorkBuddy expert personas in any conversation at any time (429 experts) with no mid-session preset lock, a tool tailor that scans local session logs for per-tool call counts, error rates and context-token cost with one-click disabling, and three install markets (SkillHub 190k+ skills, WorkBuddy connectors, 47 verified built-in services).

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

DSH session manager: delete with trash/restore/purge, restore archived sessions, recent-activity stats, continue/pause, open log folder, unread markers, fork into a new chat, workspace grouping and sorting, context compaction threshold.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

Filters tool outputs, prunes stale context and discloses skills on demand for DSH 0.2.1-alpha.1.

Context engineering and token optimization plugin for DeepSeek Harness (DSH): tool output filtering, context pruning and progressive skill disclosure for LLM coding agents

sift-light — Evidence-first search for AI agents.

AI-managed Auto Compact for DeepSeek Harness: in the Block PTC preset (DSH 0.2.2-rc.1 or newer), the agent decides when to organize context and what to retain as work progresses, without waiting for a fixed token threshold.

Knowledge base for DeepSeek Harness: assembles ContextWindow evidence at query time within heading boundaries and token budgets, with follow-up reading around each search anchor; combines BM25/vector search via weighted RRF, MMR and optional local/remote reranking; provides automatic evidence injection, a browser panel for local embedding/rerank/OCR model downloads and health checks, keyword search without model downloads, and in-place rescans of imported directories.

Execution maze for DSH sessions: the agent's real path — main advance, failed or dead-end detours, backtracks, request retries and subagent branches — drawn on one wall-clock timeline, with three tracks under each lane sharing that axis (tool-call density, token pulse, context pressure) and a deterministic analysis panel below it (tool result matrix, failure-recovery chains, duration distribution); watch it grow live in a session tab, or upload up to 5 session logs for a same-axis compare.

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.

Reversible context slimming for DeepSeek Harness: TOON-style lossless tabular re-encoding of uniform JSON arrays, stride-sampled table windows with line numbers, and cross-turn dedup for repeated tool output; every replacement passes a byte-plus-token gate (≤72% bytes, strictly fewer estimated tokens) and the original is spilled to disk behind a `[save-token #id]` notice retrievable in one call via the `save_token_expand` tool, with billed and avoided token metering on a settings dashboard.

DeepSeek Harness integration for OpenContext with durable cross-session memory, automatic prompt capture and recall, session summaries, structured insights, and document retrieval.

Request-side injection and jailbreak plugin for DeepSeek Harness: rewrites only the request copy sent to the model — system-prompt sections, fabricated turns, and keyword or regex replacement — leaving the conversation log and host files untouched; ships unrestricted / nsfw / authority presets, imports the dsh-purge 破甲 prompt as an ordinary preset, enables per agent preset, always-on, or by model and agent preset, and records each injection as a collapsible row in the session.

DocsMint workspace panel and agent tools for document search, reading, creation and updates through Cloud OAuth or self-hosted API keys.