DSH 自定义模型思考等级管理与偏好记忆插件：原生设计语言、全档位思考配置与无感隔离式跨会话偏好记忆。

Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.

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).

DSH plugin: connect to MCP servers, discover tools, and register them for direct model invocation with retry logic and statistics

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio)

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

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

The ultimate 2-way bridge between OpenAI Codex and DSH: bidirectional chat sync, live Skills mount & auto MCP mirroring.

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

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.

AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.

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.

Git-native slide format, Agent API, CLI, MCP server, and renderer

A universal, atomic library of mathematics and tools for agents to compose them.

TapTap 小游戏开放能力 mcp

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

DeepSeek Harness session cost meter plugin: session/daily cost, budget, history, OpenCode Go quota, official & custom-provider balance, Codex-like token heatmap, peak/off-peak pricing with pre-switch popup & system-notification alerts, official price sync, 90+ model pricing catalog, Coding Plan quota queries (7 vendors), bilingual zh/en 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.

DeepSeek Harness (dsh) 接入飞书/Lark bot，扫码即用：流式卡片、项目工作区、并行任务、多角色 Agent、跨会话通知、对话内模型/密钥管理与安全网守护（dsh 崩溃后飞书仍可自救）。A scan-to-connect bridge bot connecting DeepSeek Harness (dsh) into Feishu/Lark: streaming cards, workspaces, parallel tasks, multi-role agents, cross-session notify, in-chat model/key management, and a safety-net guardian.

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.

dsh plugin bundle porting the omp advisor subsystem: a per-session reviewer model that observes the primary transcript and injects severity-ranked advice (nit/concern/blocker).

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

Usage statistics for DeepSeek Harness: aggregated token and cost metering per session, per day, per week, per month and over custom date ranges, with per-model breakdown, peak-hour pricing, durable daily history, a Settings usage panel and the /usage comm