CATEGORY
Verified manifests and exact versions in this category.
@goodandready/dsh-goal
Autonomous Goal Execution & Multi-Turn Task Tracking Engine with Sticky Header for DeepSeek Harness
dsh-wecom
dsh-wecom: a WeCom AI Bot channel for DeepSeek Harness — each chat runs a persistent, preset-backed agent over the official long connection.
dsh-subagent-progress
Live subagent progress dock for DeepSeek Harness: folds each child session's events into a subagentProgress projection (turn/step, last tool, latest assistant preview, notify_user updates) and renders a frosted-glass status dock above the parent conversat
dsh-openwolf
A compact code-map 'second brain' for DeepSeek Harness: pre-indexed project maps, per-file digests, session digests, read/write interception, and AGENTS.md injection so the agent stops re-reading whole files.
dsh-office-plugin
Live office: multi-agent activity rendered as a pixi.js office of ox/horse workers, in a Web UI tab next to the trajectory view
@carljia/omd-dsh
DeepSeek Harness plugin based on the OMD philosophy: mode capability boundaries + model configuration by mode + tier-differentiated sub-agent delegation
@dsh-enhanced/assistant-evolution
Approval-gated behavioural self-evolution for the DSH personal assistant.
@dsh-enhanced/acp
Use DeepSeek Harness as an Agent Client Protocol (ACP) stdio agent.
iterate-plugin
dsh plugin that turns the iterate skill into an autonomous closed-loop harness with quality command center and experience bank (v3.3). Features: plan -> parallel review xN -> atomic fixes -> validate -> loop -> auto-stop, plus dry-run pure-review mode, qu
dsh-agent-bus
Multi-agent orchestration for DeepSeek Harness. Sessions in one workspace assign work, review results, and run DAG workflows — without you as the messenger.
@dsh-enhanced/assistant-automations
A durable, fenced cold-start scheduler and isolated Agent runner for DeepSeek Harness.
dsh-my-go
DSH plugin: Sisyphus agent orchestration — star topology, single-line blocking, 7 specialist sub-agents (Hermes/Explore/Librarian/Looker/Hephaestus/Prometheus/Oracle) with per-type model binding, go_work/continue/need_help/forward communication tools, Web
relay-dsh-plugin-manager
Conversation-first plugin discovery and lifecycle management for DeepSeek Harness.
dsh-rule-engine
DSH Rule Execution Engine v3: Container Parser for AGENTS.md + Interpreter + Matcher + Execution Framework
dsh-frostfin
Kimi Code as the agent loop of DeepSeek Harness — ACP bridge loop plugin
dsh-subagent-library
Named subagent library for DeepSeek Harness: a settings-driven roster of role subagents (model + persona + tool filter), exposed to every session through the list_subagents and delegate tools, a /subagent command, and a Settings page.
koma-miko-dsh
DeepSeek Harness adapter for Koma Miko Agent Specs.
@double-coding/flow2spec-deepseek-harness
Native DeepSeek Harness plugin for Flow2Spec
managed-agents
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
dsh-subagent-profile
Dispatch one-shot subtasks to derived subagents with per-task overrides (preset/model/provider/reasoningEffort/persona/tool whitelist), a runtime-derived cost guard, a subagent-profiles service, observability metadata, and a web-GUI settings page plus a d
dsh-plugin-omoslim
DeepSeek Harness bundle: oh-my-opencode-slim style Orchestrator agent preset with model-pinned specialist subagents (explorer/oracle/librarian/designer/fixer/council).
@huanghai-lab/dsh-custom-instructions
Custom instructions editor for the DSH web GUI: a settings page (side bar → 设置 → 自定义指令) that edits the global instruction file ~/.dsh/AGENTS.md, applied to every chat on the machine. Hot-pluggable — mounted via ~/.dsh/cordis.patch.yml + a profile node_mod
dsh-auto-evolve
Self-evolving plugin for DeepSeek Harness: observes agent behavior, proposes improvements to its own skills/policies via LLM, validates them in a sandboxed trial agent, and applies versioned mutations with rollback.
dsh-learning-mode
DeepSeek Harness (DSH) bundle that self-installs the 学习模式 (Learning Mode) agent preset — a coding agent that teaches while coding: concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning o
@starwish-ai/xingyuan-dsh
星愿 XingYuan for DeepSeek Harness: An Agent Preset bundle for creating wishes/tasks through conversation, Opportunity Day check-ins, micro-actions, memory, and charts
@hanxu131/dshacp
Zed-first ACP v1 server driving DeepSeek Harness (DSH): standalone stdio bridge with token streaming, tool calls, approval, plan, and session management
dsh-continue
Safe unattended network recovery and continuation policies for DeepSeek Harness.
dsh-subagent-default-model
Configure default model routes for DeepSeek Harness subagents, with single-model, round-robin, random, and per-route reasoning-effort options.
@openma/dsh-agents-plugins-bridge
Portable Agent Plugins, Codex, Claude Code, and Pi plugin bridge for dsh
dsh-orchestrator
[Orchestration Mode] Provides DeepSeek Harness with a multi-agent orchestration mode: the main agent decomposes and delegates tasks, workers communicate in a full mesh, and models and thinking intensity can be specified for each worker.
