# Pipelex

> Pipelex is the reference runtime for the MTHDS open standard — a declarative language for building typed, composable AI workflows as reusable .mthds files.

Pipelex is the reference runtime for MTHDS, an open standard declarative language for defining AI methods — discrete, reusable units of cognitive work like extraction, analysis, synthesis, and generation. Methods are defined in human-readable `.mthds` files built on TOML, with typed concepts (semantic data schemas) and pipes (orchestration steps with explicit inputs and outputs). Pipelex handles model routing across 60+ AI models, structured output parsing, and pipeline orchestration.

- **Declarative .mthds Language** — *Define AI workflows in typed, human-readable files that work across models — no boilerplate, no lock-in.*
- **Typed Concepts** — *Semantic types carry business meaning (not just structure), so pipes compose wherever types are compatible without manual glue code.*
- **60+ AI Model Support** — *Route to OpenAI, Anthropic, Google, Mistral, DeepSeek, Bedrock, Ollama, and more via a single gateway key or bring-your-own keys.*
- **Pipeline Orchestration** — *Chain pipes into sequences, run in parallel, batch over collections, and route conditionally — all declaratively.*
- **Claude Code Plugin** — *Describe what you want in natural language and Claude writes, runs, and iterates on your method via the MTHDS plugin.*
- **Multi-Modal Capabilities** — *LLM calls, document extraction/OCR, image generation, and web search — all as typed pipe operators in a single pipeline.*
- **Reproducible & Testable** — *Deterministic orchestration with validation, dry runs, and mocked responses — catch errors without spending tokens.*
- **MTHDS Ecosystem** — *Publish and share methods on the MTHDS Hub (mthds.sh), install versioned packages with dependency management and lock files.*

Install with `uv tool install pipelex` and run `pipelex init` to get started. Use the Claude Code plugin or VS Code extension for the best authoring experience.

## Features
- Declarative .mthds language (TOML-based)
- Typed semantic concepts with refinement hierarchies
- 60+ AI model routing via Pipelex Gateway or BYOK
- Pipeline orchestration (sequence, parallel, batch, conditional)
- Structured output generation with schema validation
- Document extraction and OCR (Azure Doc Intelligence, Docling, DeepSeek OCR)
- Image generation (FAL / Black Forest Labs)
- Web search integration (Linkup)
- Claude Code plugin for agent-authored methods
- VS Code / Cursor extension with syntax highlighting and flowcharts
- MCP integration (agents call methods as tools)
- n8n workflow automation node
- Self-hosted REST API server
- Python SDK with async execution
- CLI for init, validate, run, build, and visualization
- plxt formatter and linter for .mthds files
- Validation and dry run with mocked responses
- MTHDS Hub package publishing and discovery
- Versioned package system with lock files and SHA-256 integrity
- Cost tracking and telemetry
- Local AI support (Ollama, vLLM, LM Studio, llama.cpp)

## Integrations
OpenAI, Anthropic, Google Vertex AI, Google GenAI, Mistral AI, Amazon Bedrock, DeepSeek, Ollama, FAL (Black Forest Labs), Linkup, Docling, Azure Document Intelligence, Claude Code, n8n, VS Code, Cursor

## Platforms
CLI, DEVELOPER_SDK, API, VSC_EXTENSION

## Pricing
Open Source

## Version
0.23.5

## Links
- Website: https://pipelex.com
- Documentation: https://docs.pipelex.com/latest/
- Repository: https://github.com/Pipelex/pipelex
- EveryDev.ai: https://www.everydev.ai/tools/pipelex