Plugins

Turn your phone into the control center for an AI coding assistant CLI session (Claude or Codex) running on your computer.

A whale-girl companion for DeepSeek Harness with 45 achievements, daily quests and weekly check-ins, three mini-games, 92 artworks, 620 dialogue lines, a growth journal, weather and festival reactions, per-tool work poses, cross-device save export/import (JSON file or migration code), accessibility mode and an optional MiMo TTS bridge. Data stays in the host localStorage with no telemetry. Verified on DSH desktop 0.2.0-rc.2; compatible with 0.2.1-rc.1/rc.2 and legacy 0.1.x web.

Integrates TypeSafe Jev for skill and file selection, task supervision, shared-finding corrections, tool-output filtering, approval assistance, and recorded-stage navigation in DeepSeek Harness; all features are disabled by default.

MCP Apps Host plugin for DeepSeek Harness: renders interactive HTML cards from MCP _meta.ui in sandboxed iframes, bridges postMessage to MCP tools/call and resources/read

Authenticated mobile gateway for DeepSeek Harness: connects the companion native iOS client over WebSocket for sessions, live events, tasks, goals, approvals, commands, and file transfers, with QR pairing and device revocation.

Other memory plugins help your agent remember more. This one decides what is allowed to count: agents propose, a human approves (three-store gate + immutable audit log), and recall runs on SQLite FTS5/BM25 with zero model calls (measured p50 2.3ms). A token ledger shows what recall actually cost; one vault for DSH, Claude Code, Codex, Cursor and any MCP client.

Red-team engagement mode: send one target organization name; a planner session runs five execution roles (recon, asset triage, vulnerability discovery, exploitation, internal pivot) with configurable concurrency; preflight checks skills/resources; scoring uses four stages (recon, internet, boundary, internal) with server-side caps and privilege-wins dedup; findings stay in a local SQLite fact base. The persistent right-side console has nine pages and includes asset mapping, agents, sessions/tunnels, findings, score targets, reports, POC knowledge base and skill library. v0.15.2 adds automatic HTTP evidence/action records, batch ingest, scope check, tunnel pivot probe, data proof, cleanup ledger and T0-T3 asset admission to prevent scope drift. 59 redteam_* tools; 38 bundled skills.

Desktop feature aggregate that installs the DSH Web UI collection, dshmarket, Codex Connect, and reasoning-effort controls at pinned versions.

Bounded, layered, approval-gated, auditable cross-session memory: a typed `ctx.memory` seam with a zero-dependency SQLite provider, a `memory` tool, and frozen snapshot injection, plus the dsh-memory-protocol v1 rehearsal with an adapter registry and a distributable conformance suite.

🌌 Mebular · shared memory and task collaboration for agents. Through a DSH-native plugin, it provides cross-device, cross-agent memory sharing and task-graph capabilities — so physical devices are no longer the boundary of your agents. Secure, controllable, and decentralized! The plugin attaches to an existing Mebular app or CLI runtime; when none exists, the panel installs the shared runtime on demand, and it never starts or downloads Mebular silently.

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

Rewrites outgoing /chat/completions requests with an evolved chain-of-thought scaffold (nine-dimension genome, elitist selection with fragment crossover, one deterministic re-evaluation pass), scores answers against a fixed 20-objective baseline, and appends one line per rewrite to live-requests.jsonl in the plugin data root (default <cwd>/.aecot, overridable with AECOT_ROOT).

Code-first React and TypeScript task apps rendered inline, in Canvas, full screen, or on localhost, with interaction state available to later agent turns and approval-gated MCP and API access.

Session-scoped GeoGebra canvas with 20 native tools for drawing, scene readback, text layout checks and animation capture, plus 55 mathematical skills and bundled offline applet assets.

A pet fish you raise in DSH. No personality settings — she grows up through the event stream, and your interactions decide who she becomes. She browses Bilibili on her own, writes a diary, and brings what she finds back to ask you. Four stages and three bottlenecks advance only by what happens; only after all four does she begin to have a stance list. Her diary is hers by default; one switch in settings and you can read it. Records in the event stream can never be deleted, so it remains the only trustworthy source. Zero runtime dependencies.

Base aggregate for DeepSeek Harness Desktop features: Web UI collection, plugin market, Codex Connect, and reasoning controls.

Personal center for DeepSeek Harness: cross-session usage statistics with per-provider and per-model breakdown (auto-discovers configured models), per-model cost estimation, global custom instructions, a data-driven desktop pet with bitmap & vector skins, and a conversation status overview, all local and offline.

Volcengine Ark provider plugin for DeepSeek Harness (DSH): registers Agent Plan, Coding Plan, and postpaid routes on the native pi-ai adapter so Ark models appear in the model picker.

MCP Connector for DeepSeek Harness: a specialist MCP marketplace and 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.

Risk-gated approval automation for DeepSeek Harness: flash pre-classifies whether a write/command is irreversible — safe operations are auto-approved, dangerous ones are escalated to human approval (fail-safe). File-diff review with one-click revert and session-scoped snapshots (v0.5.1: precise snapshots via tool-call parameter tracing, incl. human-approval cases).

Connect any ACP-capable agent to DSH and use DSH as a single entry point for all conversations and tasks. Models, thinking levels and permission modes come from the agent itself; tool calls appear in the main chat, diffs are collected on a dedicated NTR page, and approval requests appear in the composer. Requires an ACP-capable agent CLI installed locally.

Notification reminders, message alerts and desktop notification for DSH — a desktop notifier that raises a system toast, a sound and a tab-title marker when the agent needs your input (approval, plan review, question) or a reply is finished in the background (task complete / completion alerts, notify when done); the Settings page holds the master switch, sound and volume, the per-case toggles and the zh/en notification language.

Turns explicit DSH session experience into reviewable native Skill drafts that are saved only after user approval.

Asset governance console for self-hosted AI infrastructure. Registers MCP servers, skills, agents, AI apps, model channels, SaaS connectors and NAS storage in one ledger with a lifecycle state machine, per-tool RBAC permission points, department x agent x skill cost attribution, dependency topology and an append-only audit trail. Self-hosted, MIT, no hosted tier and no cloud contract.