Crash-proof LLM pipelines. Resumes from failure without a database.
DagPipe makes LLM pipelines crash-proof by saving each completed node's output to a plain JSON file. When a pipeline fails, re-running it skips finished nodes and resumes from exactly where it stopped. No database, no broker, just files.
Built for developers who are tired of losing pipeline progress to timeouts, rate limits, and bad model responses. Especially useful when running multi-step workflows on free tier APIs where every failed node costs real quota.
Ships with smart model routing by task complexity, Pydantic schema validation with auto-retry on malformed output, dead letter queue for failed nodes, context isolation so nodes only see their declared dependencies, and an MCP server for generating pipelines directly from Claude Desktop, Cursor, or Windsurf.
Valid MCP server (1 strong, 1 medium validity signals). 1 known CVE in dependencies Package registry verified. Imported from the Official MCP Registry. Trust signals: 3 highly-trusted packages.
9 files analyzed · 2 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Set these up before or after installing:
Environment variable: GROQ_API_KEY
Environment variable: GEMINI_API_KEY
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-devilsfave-dagpipe": {
"args": [
"-y",
"structured-extract"
],
"command": "npx"
}
}
}Once installed, try these example prompts and explore these capabilities:
No written reviews yet. Be the first!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.