333 results
Memory protocol enforcement plugin for DeepSeek Harness — forces memory_weave before tool calls, auto-ingests session turns, injects memory context into agent steps. Bridges the opencode-memory MCP server with a hard protocol gate.
Witness — the quality gate for agent-built web apps. Independent browser acceptance testing: CLI, MCP, AI-drafted checklists, visual regression, multi-browser. Agents self-test and pass; real browsers tell the truth.
JumpServer asset lookup for DeepSeek Harness: query assets via conversation using AccessKey/SecretKey signed requests
Server-development mode for DeepSeek Harness: remote agent tools (ssh_list / ssh_exec / ssh_ls / ssh_read / ssh_write) backed by a persistent ssh2 engine, so the DSH coding agent's working environment is a remote Linux server. Works with the `remote` agent preset.
Out-of-tree dsh web-profile bundle: enables --host 0.0.0.0 and gates the Web UI behind a --web_token access token (cookie after first ?web_token= open). Forks @deepseek-ai/dsh-host-webserver and @deepseek-ai/dsh-web-app/startup.
MCP Tools panel for the DeepSeek Harness Web GUI: see every MCP server and tool available in your session, grouped by server, with transport info, JSON schemas, live search and last-used times derived from real session logs.
DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and one shared DSH provider carrying both slots' models with four thinking-effort levels.
Ask any line of code its backstory: what it does, and why it's here — grounded in git history and the agent's own session log. Ships a DeepSeek Harness plugin and a standalone MCP server.
DSH WebUI capability controls for skills, MCP servers, tools, prompt injections, approvals, and safety guards at session, project, and global levels.
本地优先的 Agent 五层记忆体组件 - DSH 插件
IDE engineering services for DeepSeek Harness: LSP diagnostics/navigation/rename, DAP debugging (debugpy + js-debug), and task-toolchain build/test/lint runs.
分层长期记忆 MCP 服务器：本地 MiniLM 或 OpenAI 兼容嵌入 API，供 LLM Agent（DeepSeek Harness / Claude Code）做可语义检索的长期记忆
DSH plugin — browse local Hermes skills / MCP servers / chats in the DeepSeek Harness web sidebar, and inject selected skills & MCP config into the active agent (active/passive mode).
Selectable Codex model provider for DeepSeek Harness over the local Codex app-server
DeepSeek Harness 本地开发服务控制台（原生插件）：发现监听端口，识别服务归属，安全查看/停止/重启。Local development service console for DSH.
MCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.
GitHub official MCP server bridge for DeepSeek Harness: registers mcp__github__* native tools via @deepseek-ai/dsh-mcp-client, plus a github_file_read tool that reads file contents over REST (fills the gap where the MCP bridge discards resource content).
Academic Paper Search bridge for DeepSeek Harness: verified multi-source literature search over the existing MCP server.
dsh plugin: daily RSS news digest from 46 curated sources, LLM-edited via the model already configured in dsh, delivered to your IM via webhook (ServerChan / PushDeer / WeCom / Telegram / Bark / gotify / custom).
KnowLP-RAG: dual knowledge-graph retrieval for Markdown notes — DeepSeek Harness (dsh) bundle: MCP server + native Cordis plugin
Cloud workspaces for DeepSeek Harness: pick "Cloud (SSH)" in the workspace chooser and the agent's bash/read/write/edit/glob/grep tools transparently run on your Linux server over SSH. Includes ssh_* agent tools, an SSH host settings card, jump-host support and persistent connection pooling.
Per-workspace Skill and MCP enablement for DeepSeek Harness: each project controls which skills and MCP servers new sessions load.
DeepSeek Harness SSH 远程运维插件，支持远程命令、文件管理、JumpServer 与 keyboard-interactive 认证
Host file-browser web app over the dsh webserver with a /dsh-agfs command