Plugins

Forgetting-curve in-place dialogue compression for DeepSeek Harness: recent turns stay verbatim, middle turns are structurally dehydrated (zero-LLM), ancient turns fold into a bounded summary pair — unbounded conversations on a bounded memory budget.

An accumulated design-taste corpus for DSH agents: feed good and bad examples, distill principles, and review new designs against learned judgment rather than a fixed ruleset.

Codex-style /btw command: answer side questions in a conversation-seeded subagent (fork provider), rendered in the UI without entering the main session history.

Local cross-session messaging for DSH agents, with discovery, cold-session wake-up delivery, and auditable message history.

Local long-term schedule panel: top-bar "日程" text button, today/week/history month-calendar views with stats, completion checkmarks with per-day history, schedule↔conversation links with click-to-jump, recurring tasks (daily/weekly), optional auto carry-over for unfinished one-time tasks, and dailytask_* agent tools.

Durable DAG workflows for DeepSeek Harness with Agent authoring tools, SQLite persistence, resumable runs, and a visual Canvas Studio.

Device channel between the agent and your own phone: it sends files it just produced, and you @-reference what your phone sent back. End-to-end encrypted P2P through the SwarmDrop CLI, with no account and no public IP; node status, paired devices and QR pairing sit in a sidebar panel.

Ownership-checked tools and HTTP routes to list, release and permanently delete subagent sessions, with automatic web UI refresh after deletion.

Runs 3 or 5 coding-agent candidates in detached Git worktrees, validates their patches with project commands, ranks only passing candidates, and requires separate approval before applying the winner.

An independent approval subagent judges every sandbox escalation, with a configurable model and an audit log.

Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with templates, a gate that blocks writes to protected files without a one-time approval token, zero-judgement event logging, weekly distillation, and a TDD execution-loop skill.

ZCode-style persistent project memory with a full settings manager, index-first injection and agent memory tools.

Adds session, project, and global controls in the DSH WebUI for skills, MCP servers, tools, prompt injections, approval escalation, and safety guards; enforcement is scoped to the current agent.

Multi-agent orchestration for DeepSeek Harness -- specialized agents, task orchestration, workflow skills

A self-evolving plugin for DeepSeek Harness: it observes how the agent runs, proposes improvements to its own assets via the LLM, validates each proposal inside a sandboxed trial agent, and applies only verified mutations — with a versioned ledger and automatic rollback on regression.

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

AIEO (GEO/AEO) delivery method as one isolated skill provider: AI-visibility diagnosis on a 0-9 score, positioning, search-term mining restricted to whitelisted platform exports, periodic monitoring and an HTML monitoring dashboard, chained by one shared question library, plus a landing-page cloner.

Per-execution HTTP/SOCKS5 proxy routing for Agent fetches, LLM providers, and shell commands, with settings-backed hot reload, approval-gated controls, and credential-safe status.

Decision split view for DSH web UI: a decision summary card in the main window plus the full plan in an independently scrollable side panel, so you can review the whole plan while writing decisions and send them back to the agent with one click.

Local image, voice, music and SFX generation plus transcription, with pinned identity: characters, animals, objects and actor voices are defined once and reused on every later call, degenerate output (a near-flat image, silent audio) is rejected instead of returned as success, and a generated line can be read back as text so a clone that swallowed its ending becomes visible. The engines unload when idle, and image generation and transcription can each be pointed at an OpenAI-shaped API instead of the local Vulkan backend.

Plug/unplug any DeepSeek Harness plugin cleanly — list every mounted layer (bundles + patch rows), remove with full cleanup, disable/enable without deleting, and audit for orphaned/dangling state. CLI + agent-callable unplug tool. Read-only by default; destructive operations require explicit confirmation.

Adds a native Store section to DSH Settings for catalog search, tag filtering, sorting, installation, and installed-plugin management.

Interval heartbeat that wakes each root agent itself (followup injection) to proactively report progress, risks or blockers: busy-safe queuing, no stacking, auto-pauses when no human replies, re-arms on the next user message.

Nightly self-improvement for your DeepSeek Harness agent: harvest past sessions offline, replay recurring tasks on your own API budget, and consolidate validated skills behind a held-out gate. Brings microsoft/SkillOpt's SkillOpt-Sleep engine to dsh as native tools plus a bundled skill - no weight training. Requires Python 3.10+ and the SkillOpt-Sleep engine (pip install skillopt).