Orchex

Autopilot AI orchestration — describe your intent, orchex auto-generates a plan, parallelizes it into streams with file ownership enforcement, self-heals failures, and routes across 6 LLM providers. Supports Claude, OpenAI, Gemini, DeepSeek, Ollama, and AWS Bedrock.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://orchex--wundam.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "Orchex": {
      "url": "https://orchex--wundam.run.tools"
    }
  }
}

能力清单

工具	说明
init	Initialize a new orchestration for a feature. Creates .orchex/active/manifest.yaml with streams.
add_stream	Add a new stream to the active orchestration.
status	Get the current orchestration status and progress.
execute	Run the orchestration. Each call executes one wave of streams in parallel via LLM API, applies artifacts to the codebase, and runs verification commands. Call repeatedly for each wave, or use auto mode.
complete	Mark a stream as complete, or archive the entire orchestration.
recover	Recover streams stuck in in_progress state or failed state. Auto-detects stuck streams and resets them to pending for retry, or skips them.
learn	Parse a planning document and generate stream definitions. Returns proposed streams for review before initialization.
init-plan	Generate an annotated markdown plan template that teaches users how to structure documents for orchex learn. Creates a starter plan file with inline comments explaining what the learn pipeline parses.
auto	Generate a plan from user intent, preview streams, and optionally execute. Flow: gather context → LLM generates plan → learn pipeline → preview → approve → execute → report.
reset-learning	Reset learning data: thresholds, events, patterns, and/or reports.
rollback-stream	Revert file changes made by a specific stream using git.
reload	Restart the MCP server to pick up rebuilt code. MCP client will reconnect automatically.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。