Enables AI coding agents like Claude Code or Codex to delegate tasks to a DeepSeek Harness subagent with its own context window, providing tools for task delegation, result waiting, continuation, and supervision with sandboxed execution.
Lets MCP clients like Codex delegate independent sub-tasks to DeepSeek as a sub-agent via a single tool, with optional context, custom system prompts, and configurable model/temperature settings.
MCP server that lets AI agents discover, inspect, install, and run DeepSeek Harness plugins via MCP, bridging the gap between the MCP protocol and Cordis-based plugin bundles.
A Codex MCP server that delegates exploration and implementation tasks to DeepSeek via Claude Agent SDK, supporting subagent types and task persistence.
Allows seamless integration of DeepSeek's language models with MCP-compatible applications like Claude Desktop, supporting features such as model selection, temperature control, and multi-turn conversations with automatic model fallback.
Enables ChatGPT (or any MCP client) to delegate coding tasks to a local Hermes-backed agent with async job management, supporting read-only investigation, implementation, and continuation of sessions via secure MCP tunnel.
A Model Control Protocol server implementation that allows Claude Desktop to use Deepseek models running in Docker, enabling seamless integration between Claude Desktop and Deepseek's language models.
Enables MCP-capable AI harnesses to interact with DeepSeek Web using an authenticated browser session, supporting prompts, deep think, search, image recognition, file attachments, and local SKILL.md injection.
This MCP server enables Codex to delegate bounded subtasks to DeepSeek Harness through MCP, with persistent JSON mailbox messaging and proactive task initiation via Codex app-server. It provides tools for delegation, message exchange, and task status tracking.
Connects a DOT main chat to an already-running Harness instance so it can submit native tasks with progress, replies, queue controls and verified cancellation, page through original history, run keyword history searches, and discover project files with bounded line/tail reads and literal content search. It also handles native interactions, permission reconciliation and explicitly scoped deployment planning and evidence reads, with stable run/operation IDs and idempotency keys for recovery after timeouts or disconnects.
Enables agents to search a lightweight catalog, inspect permissions, lazily start trusted MCP servers, and call child tools without keeping all schemas in context. It also loads approved skills on demand and routes third-party additions through a human approval queue.
Lets Claude Code, Codex, or any MCP client drive DeepSeek Harness as a long-lived coding agent: starting and resuming conversations, dispatching tasks in the background, streaming live output and reasoning stats, interjecting or interrupting mid-turn, handling approval prompts, and collecting results later. Sessions persist by ID, so work survives process restarts and can be handed back to a DSH GUI when needed.
Lets any MCP-capable coding harness (Cursor, Claude Code, Codex, Gemini CLI, VS Code/Copilot, opencode, and others) hand a self-contained task to a real, isolated DeepSeek Harness process that works in a chosen workspace with its own context window, model, and toolchain, then returns the final answer. Exposes task submission with time estimates and acceptance criteria, status polling with live progress and process-tree telemetry, graceful cancel and forced kill of whole process trees, and a health probe reporting concurrency, deadlines, and recent jobs.
Diagnoses the Codex MCP launch path and writes host configuration so Codex, Cursor, or Claude Code can spawn the dsh profile. It does not run the MCP stdio server in the Web process.
Facilitates two-stage reasoning processes using DeepSeek for detailed analysis and supports multiple response models such as Claude 3.5 Sonnet and OpenRouter, maintaining conversation context and enhancing AI-driven interactions.
Enables multi-round brainstorming debates between multiple AI models like GPT, DeepSeek, and Ollama to produce synthesized final outputs. Users can orchestrate parallel model interactions where AI agents critique and refine each other's ideas to reach a consolidated conclusion.