Read-only GitHub access for agents, wrapping several tools. Inside the tool it automatically probes and selects whichever GitHub access method works locally, and tries network proxies on its own. That cuts down the network and parsing problems an agent may hit when accessing GitHub, and the overhead of it repeatedly trying different approaches.
DeepSeek Harness cross-session long-term memory + user profile plugin: the AI remembers who you are, your projects and preferences across sessions. Pure Markdown, zero-config, fully local. (monorepo: dsh-memory-core + dsh-memory-ui)
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
A playable pixel companion plugin for DeepSeek Harness (DSH): platform-jumps over chat messages, WASD controllable, with a full nurture system fed by your agent's real token usage.
Native interactive Git diff review for DeepSeek Harness with structured annotations sent back to the current Agent session. DeepSeek Harness 原生交互式 Git diff 审查，支持结构化批注并回传当前 Agent 会话。
DSH 的 fork 伴随插件:fork 后把原会话的子 agent 复制到新对话,并保持可继续发消息 / Copy a session's subagents onto a forked DSH conversation and keep them reachable. Co-developed with AI.
Find DSH plugins across five community catalogs plus live GitHub and npm search, ranked by relevance × trust × freshness × popularity — not stars alone. 跨五个社区目录并叠加 GitHub 与 npm 实时搜索来找 DSH 插件，按相关度 × 可信度 × 新鲜度 × 热度排序，而不是只看 star。
Windows desktop UI context picker for AI agents: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, local OCR, and user-approved MCP output. Works with OpenAI Codex, DeepSeek Harness, and other MCP-compatible clients.
DSH agent presets whose leader does no work itself: non-management tool calls are denied at the harness boundary and every task goes to a subagent (a second preset deliberately picks weaker models for harder tasks).
