Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.

DeepSeek Harness MCP Connector: connect servers, search tools across active connections, and troubleshoot discovery. Includes a continuously updated catalog; supports OAuth 2.0 PKCE, API keys, Streamable HTTP/stdio, and mcpServers JSON import.

Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.

Open-source quantum Agent workspace with a desktop client, Web UI, messaging, Qiskit/MCP tools, and scientific validation

Manage MCP servers (stdio / streamable-http) for dsh web; tools are reached only through four middleware tools. DSH MCP 管理器：Web 侧边栏「MCP」入口，面板按状态分级展示 MCP 服务器（运行中/连接中/已配置/失败），支持快速接入（stdio / streamable-http 表单）与粘贴 mcpServers JSON 导入。已连接服务器的工具一律经中间层工具（ws_mcp_

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

Composable mathematics tools for agents

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

Cost tracking for DeepSeek Harness: session and model costs, token usage, budgets, provider balances, and coding-plan quotas. Bilingual English/Chinese UI.

DeepSeek Harness plugin for previewable cross-preset session migration. Fixed-schema handoffs preserve state, source-model intent, and unresolved images; the original session stays untouched.

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。

DSH model-facing Office tools: create, read, and update Word (.docx), Excel (.xlsx), and PowerPoint (.pptx) files inside the session workspace, entirely through the official DSH filesystem service.

DeepSeek Harness companion for ClineBot / ClinePass: dynamic subscription models sync, quota exhaustion warnings, session metrics, dedicated settings page, live usage limits, and /cline slash-command.

Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.