플러그인

DeepSeek Harness용 3계층 로컬 메모리: L1 스냅샷 메모리(MEMORY.md/USER.md)를 memory_* 도구로 필요할 때 읽기 + L2 검색 가능한 지식 베이스(사실 + SQLite FTS5, 슬라이딩 윈도 토큰화 기반 중국어 검색) + L3 Hermes/Claude Code/Codex/WorkBuddy 및 승인된 Agent Hub 문서(memory/global, memory/projects, 승인된 결정)에서 가져오기(콘텐츠 해시 중복 제거). v0.2.0은 모든 자동 주입을 제거해 모델이 12개 memory_* 도구 중 하나를 호출할 때만 메모리가 컨텍스트에 들어가고 데이터는 로컬 드라이브에 남습니다.

DeepSeek Harness 에이전트 기능을 MCP 서버로 노출해 외부 MCP 클라이언트(예: Hermes)가 Harness를 구동해 코딩 작업을 수행하도록 함. Hermes = 두뇌, Harness = 팔

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

Security-audit facts AI coding agents cannot compute, plus a verdict gate: euthyna history attributes deleted lines to commits and flags those from security fixes (--origins finds the first introducer), euthyna coverage reports which changed symbols no test ever invoked, and euthyna gate checks each finding against six gates, downgrading any without evidence to an observation.

Pool AI provider accounts per platform and route them through a local loopback proxy that bridges the OpenAI, OpenAI-Responses, Anthropic and Gemini protocols, then write the proxy into Codex, Claude Code, Gemini CLI, Grok, OpenCode, OpenClaw and Hermes config files with snapshot-and-rollback safe writes; registers no agent tools.

dsh (DeepSeek Harness) 跨 agent 信箱插件：让 dsh 会话内的 agent 通过 agent-mailbox 与本机其他 agent（Claude Code / OpenCode / Hermes…）互发消息、收任务卡、卡动即唤醒。零 npm 依赖，Node 22 即装即用。

Bidirectional bridge between Hermes Agent and DeepSeek Harness. Hermes dispatches focused tasks via JSON-RPC over POST /mcp/collab (one-shot or continuable, nonce-bound amend, secret-bound consult reply); DSH lets you continue Hermes sessions as native DS

DeepSeek Harness web UI용 Git 소스 관리 사이드바: 저장소 초기화, 스테이징, commit/push/pull, 브랜치 및 원격 관리, AI가 생성하는 Conventional Commits 메시지, 커밋 기록 그래프.

DeepSeek Harness용 영구 장기 페르소나 메모리: MEMORY.md/USER.md 저장, memory + memory_search 도구, 요청별 컨텍스트 주입, 비밀 정보 스캔. pi-hermes-memory의 설계 철학을 이식

Cross-agent token usage dashboard: aggregates local conversation logs from Claude Code, OpenCode, Cursor IDE, DSH, OpenClaw, CodeWhale, Hermes and more into a persistent ledger that survives log deletion, with cache-hit rate, cost estimation, period comparison and day drill-down analytics in a sidebar panel.

Scoped persistent memory for DSH: memory_save/search/replace/remove/list across global, user, project and failure scopes, DSH storage-domain persistence with secret and prompt-injection scanning, session-scope search, retention cleanup, and optional session-start injection; standing context via memory_pin/memory_pins/memory_unpin.

Tiered task queue as the single source of truth for DSH↔Hermes work (reset > approve > review): enqueue tools for all submission paths, lease/claim model with concurrency 1, priority aging against starvation, atomic busy mutex, and a Hermes-side consumer (cron */1 + monitor gating) that drains tasks, writes review-handoff requests with single-slot checks, and invokes the reset agent.

Auto-approval agent for DSH permission requests: rule layer (denyAlways/allowlist) plus Hermes Pro semantic adjudication with quick-fail retries, fail-closed to human when Hermes is unavailable, rejection feedback returned to the requesting session, and approve tasks enqueued into the task queue with a shared busy mutex.

A standalone desktop pet for the DeepSeek Harness web GUI, powered by your local Hermes Agent — with real conversation, long-term memory, and persona.

Nous Portal free-tier provider for dsh: Portal OAuth (device-code) agent-key lifecycle behind an OpenAI-compatible harness route

Hermes-style self-evolution for DeepSeek Harness: a skill_manage tool that lets the agent save proven procedures as skills, prompt guidance for when to save them, usage tracking, and a background curator that keeps the self-authored skill library healthy

给 DeepSeek Harness（DSH / DeepSeek Hermes）加语音能力的社区插件：输入框语音输入（可配快捷键）+ 回答朗读（微软 Edge 神经网络音色，可换音色、可试听），无需 API Key。

Task-queue execution endpoint for DSH: requires a separately self-deployed Hermes Agent gateway plus your own WeChat inbound script; verified on a single environment — expect to adapt it.

Import chat history and memory from other AI agents (Claude Code, Codex CLI, Gemini CLI, Aider, Cline, OpenCode, Hermes Agent, OpenClaw) into DeepSeek Harness