插件

Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

上下文洞察面板：一眼看清模型上下文窗口的组成与变化——构成对照窗口大小、按请求历史趋势、压缩/注入事件、消息级 token 统计。

DeepSeek Harness plugin that connects to a PowerContext Server over HTTP for recall, memory, handoff, experience, and skills.

LLM-free lossless* compaction engine for DeepSeek Harness

上下文注入审计：统计指令链/技能目录/工具 schema 的 token 成本，检测重复与冲突。

MCP server manager plugin for DeepSeek Harness: Settings → MCP page, OAuth (PKCE + dynamic client registration) or static-token auth, tools registered as mcp__<name>__*

给所有 AI 工具和 Agent 共用的一层记忆：注入 Context Bundle、提示时检索、MCP 工具与回合结束 DSH 线程捕获。

Inject rules when needed, without wasting context. DSH port of opencode-stream-rules.

为 DeepSeek Harness 提供右侧悬浮栏以及 /context 命令，用环形图实时展示当前上下文 token 用量与分配及消费估算。

渐进披露 MCP 网关：用 `mcp_search` 检索大型远程工具目录，再由 `mcp_call` 按精确 schema 调用，并采用惰性连接与有界缓存。

局域网访问：Web GUI 绑定 0.0.0.0 + crypto.randomUUID polyfill（修复非安全上下文下 RPC 崩溃）。

Incremental file mounting with read dedupe: mounted line ranges are never re-sent to the model, on-disk changes invalidate and remount, with a Mounted Files tab and token-savings accounting.

Expose DeepSeek Harness agent capabilities as an MCP server, so an external MCP client (e.g. Hermes) can drive Harness to execute coding tasks. Hermes = brain, Harness = arms.

Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace-scoped recall, and fully configurable keys — plus sliding-context aware

在 DSH Session 与已授权 Agent Team Room 之间异步传递 LLM 总结的上下文，支持即时快照与定时摘要。

四模块会话伴侣：对话智能导出（Markdown/PDF/JSON/PNG 长图、隐私脱敏、批量 ZIP）、上下文交接摘要（模板保存与导入继承）、API 成本优化（官方动态计价、峰谷调度、日/月双档预算、模型路由）、全局对话检索与对话内搜索（Ctrl+F、CSS Custom Highlight API）。

GPU-aware execution layer for DeepSeek Harness: gpu_status / gpu_exec / gpu_run_bg tools, per-step GPU context injection, automatic CUDA_VISIBLE_DEVICES card selection

Context compression skill for DeepSeek Harness -- intelligent conversation summarization

Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, and secret scanning. Ported in spirit from pi-hermes-memory.

Logical-call context taxonomy for the DeepSeek Harness Web profile

A DeepSeek Harness plugin that integrates claude-mem: query, context injection, manual save, and session lifecycle over a local claude-mem worker's HTTP API

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

增加规格工件、技能、命令、由 goal 驱动的实施流程和任务进度上下文。