🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON evidence. | 🥇 全网最强的 DeepSeek Harness 免费联网搜索插件，免费免注册免 API key。为不能联网的模型补上搜索，问网页或 X，拿回结构化 JSON 证据（搜索、抓取、引用）。
Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent model/tools, Run Center and Token insights.
DSH x Blender direct realtime plugin v1.0 — let an AI model drive Blender over a direct TCP channel: viewport frames, custom-angle renders, inner-loop search, render profiling, safe decimation, headless offload, one-call GUI launch (15 tools + blender_rt_plan: 28 families / 183 ops). 配套 skill：sixtysevenlf/dsh-skill-blender-modeling
🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.
Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.
Proactive associative memory for DSH: system-prompt recall before the model speaks, three-layer auto-consolidation, skill crystallization, and Astra-style context management - handoff ledgers, PLAN whiteboard, water-level sensing. Local-first, model-agnostic, zero deps. 主动联想记忆+Astra 式上下文管理：自动唤回/自动沉淀/技能固化/交接账本与白板跨窗口续命/水位感知。
蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.
Reasoning-effort editing for third-party models in DeepSeek Harness: per-model thinking levels with a knowledge base + protocol inference, edited inside the official Models page card.
RETIRED 2026-10-05 — the official DeepSeek Harness now ships native continuable subagents (subagent with backgroundMode: continuable, plus send_message / interrupt_agent / list_agents / job_*). Use those instead.
Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command, reflex arcs fire with zero model calls, memory consolidates while idle, every failure is attributed before retry. Reproducible offline, MIT.
Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes. DeepSeek Harness 辅助模型插件：为视觉理解、上下文压缩、审批审查、子代理、会话标题与图片生成提供独立的模型路由、工具与系统提示，全程不触碰主对话模型。
SGME 拾光记忆引擎：AI 全面接管记忆、技能库、WIKI 知识库三大模块，跨会话、多智能体共享记忆，AI 会一直记得你的偏好。ShiGuang Memory Engine · AI takes full charge of three core modules — memory, skills, and wiki knowledge base. Memory is shared across sessions and multiple agents, so your AI always remembers your preferences.
