# Pipelex

> Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

- **Category:** AI Agents
- **Licence:** Other
- **Latest version:** v0.93.1
- **Open source:** source_available
- **Languages:** Python
- **Platforms:** Docker, pip
- **Tags:** API, Mcp, REST API, Ai Agents, Ocr, LLM, Image Generation, Web Search, Docker, AI, Python, Fastapi, Self Hosted, Web App, Codex, Claude code, Llm Orchestration, AI Methods, Mthds, Deterministic AI, Typed Pipelines, Pipelex

## Description

Pipelex lets software teams turn repeatable information-processing tasks — invoice extraction, contract review, HR screening, competitive intelligence — into version-controlled, typed AI methods. You describe the work in natural language; the plugin for Claude Code or Codex writes a .mthds file with explicit steps, typed inputs/outputs, and conditional routing. That single file then runs in three ways: as a FastAPI-based REST API (Docker image pipelex/pipelex-api on port 8081), as an MCP connector for ChatGPT or Claude, or as a generated Next.js web app. The runtime handles model routing across OpenAI, Anthropic, Google, Mistral, Bedrock, local models (Ollama, vLLM, llama.cpp), and adds OCR, image generation, and web search via optional extras. Configuration lives in ~/.pipelex with environment-variable overrides; authentication for the API server supports API-key or JWT modes. The code is source-available under Elastic License 2.0 (no managed-service resale), with a hosted SaaS tier and a fixed-price implementation service.

## Links

- [Homepage](https://github.com/pipelex/pipelex)
- [Website](https://pipelex.com)
- [Docker](pipelex/pipelex-api)
- [Demo](https://go.pipelex.com/demo)
- [Documentation](https://docs.pipelex.com/latest/)
- [GitHub Repository](https://github.com/Pipelex/pipelex)
- [Discord Community](https://go.pipelex.com/discord)
- [MTHDS Hub](https://mthds.sh)
- [YouTube Channel](https://www.youtube.com/@PipelexAI)

---
Source: https://selfhost.directory/project/pipelex