pipelex 0.20.3

Execute composable AI methods declared in the MTHDS open standard

Executable AI Methods

Pipelex is the reference Python runtime and Claude Code plugin for the MTHDS open standard.
Readable by humans, executable by agents. No boilerplate, no lock-in.

An AI method is a multi-step workflow that chains LLMs, OCR, image generation, and more — each step typed and validated.
Executable means each method becomes a new tool — agents and skills can call it, and it also runs standalone via CLI, Python, or REST API.

Demo - Documentation - Hub - Report Bug - Feature Request

Quick Start

Path A: With Claude Code (Recommended)

Install the MTHDS skills plugin:

/plugin marketplace add mthds-ai/skills
/plugin install mthds@mthds-ai-skills

Build your first method:

/mthds-build A method to analyze a Job offer to build a scorecard, then batch process CVs to score them, if a CV fits, generate 5 questions for the interview, otherwise draft a rejection email

Run it:

/mthds-run

Path B: Without Claude Code

pip install pipelex
pipelex init

Then:

1. Install the VS Code extension for .mthds syntax highlighting
2. Browse methods on the MTHDS Hub for inspiration
3. Author your own .mthds methods based on these examples
4. Validate with pipelex validate bundle your_method.mthds
5. Run them with pipelex run bundle your_method.mthds
6. View the flowchart in VS Code thanks to the extension
7. Use the mthds npm package to package and publish methods on the hub

Configure AI Access

To run methods with AI models, choose one of these options:

Option A: Pipelex Gateway (Recommended)

Get free credits with a single API key for LLMs, document extraction, and image generation across all major providers (OpenAI, Anthropic, Google, Azure, and more).

1. Get your API key at app.pipelex.com
2. Add it to your .env file: PIPELEX_GATEWAY_API_KEY=your-key-here
3. Run pipelex init and accept the Gateway terms of service

Option B: Bring Your Own Keys

Use your existing API keys from OpenAI, Anthropic, Google, Mistral, etc. See Configure AI Providers.

Option C: Local AI

Run models locally with Ollama, vLLM, LM Studio, or llama.cpp — no API keys required. See Configure AI Providers.

Example: CV Batch Screening

cv_batch_screening.mthds

[concept.CandidateProfile]
description = "A structured summary of a job candidate's professional background extracted from their CV."

[concept.CandidateProfile.structure]
skills       = { type = "text", description = "Technical and soft skills possessed by the candidate", required = true }
experience   = { type = "text", description = "Work history and professional experience", required = true }
education    = { type = "text", description = "Educational background and qualifications", required = true }
achievements = { type = "text", description = "Notable accomplishments and certifications" }

[concept.JobRequirements]
description = "A structured summary of what a job position requires from candidates."

[concept.JobRequirements.structure]
required_skills  = { type = "text", description = "Skills that are mandatory for the position", required = true }
responsibilities = { type = "text", description = "Main duties and tasks of the role", required = true }
qualifications   = { type = "text", description = "Required education, certifications, or experience levels", required = true }
nice_to_haves    = { type = "text", description = "Preferred but not mandatory qualifications" }

[concept.CandidateMatch]
description = "An evaluation of how well a candidate fits a job position."

[concept.CandidateMatch.structure]
match_score        = { type = "number", description = "Numerical score representing overall fit percentage between 0 and 100", required = true }
strengths          = { type = "text", description = "Areas where the candidate meets or exceeds requirements", required = true }
gaps               = { type = "text", description = "Areas where the candidate falls short of requirements", required = true }
overall_assessment = { type = "text", description = "Summary evaluation of the candidate's suitability", required = true }

[pipe.batch_analyze_cvs_for_job_offer]
type = "PipeSequence"
description = """
Main orchestrator pipe that takes a bunch of CVs and a job offer in PDF format, and analyzes how they match.
"""
inputs = { cvs = "Document[]", job_offer_pdf = "Document" }
output = "CandidateMatch[]"
steps = [
  { pipe = "prepare_job_offer", result = "job_requirements" },
  { pipe = "process_cv", batch_over = "cvs", batch_as = "cv_pdf", result = "match_analyses" },
]

Click to view the supporting pipes implementation

[pipe.prepare_job_offer]
type = "PipeSequence"
description = """
Extracts and analyzes the job offer PDF to produce structured job requirements.
"""
inputs = { job_offer_pdf = "Document" }
output = "JobRequirements"
steps = [
  { pipe = "extract_one_job_offer", result = "job_offer_pages" },
  { pipe = "analyze_job_requirements", result = "job_requirements" },
]

[pipe.extract_one_job_offer]
type        = "PipeExtract"
description = "Extracts text content from the job offer PDF document"
inputs      = { job_offer_pdf = "Document" }
output      = "Page[]"
model       = "@default-text-from-pdf"

[pipe.analyze_job_requirements]
type = "PipeLLM"
description = """
Parses and summarizes the job requirements from the extracted job offer content, identifying required skills, responsibilities, qualifications, and nice-to-haves
"""
inputs = { job_offer_pages = "Page" }
output = "JobRequirements"
model = "$writing-factual"
system_prompt = """
You are an expert HR analyst specializing in parsing job descriptions. Your task is to extract and summarize job requirements into a structured format.
"""
prompt = """
Analyze the following job offer content and extract the key requirements for the position.

@job_offer_pages
"""

[pipe.process_cv]
type = "PipeSequence"
description = "Processes one application"
inputs = { cv_pdf = "Document", job_requirements = "JobRequirements" }
output = "CandidateMatch"
steps = [
  { pipe = "extract_one_cv", result = "cv_pages" },
  { pipe = "analyze_one_cv", result = "candidate_profile" },
  { pipe = "analyze_match", result = "match_analysis" },
]

[pipe.extract_one_cv]
type        = "PipeExtract"
description = "Extracts text content from the CV PDF document"
inputs      = { cv_pdf = "Document" }
output      = "Page[]"
model       = "@default-text-from-pdf"

[pipe.analyze_one_cv]
type = "PipeLLM"
description = """
Parses and summarizes the candidate's professional profile from the extracted CV content, identifying skills, experience, education, and achievements
"""
inputs = { cv_pages = "Page" }
output = "CandidateProfile"
model = "$writing-factual"
system_prompt = """
You are an expert HR analyst specializing in parsing and summarizing candidate CVs. Your task is to extract and structure the candidate's professional profile into a structured format.
"""
prompt = """
Analyze the following CV content and extract the candidate's professional profile.

@cv_pages
"""

[pipe.analyze_match]
type = "PipeLLM"
description = """
Evaluates how well the candidate matches the job requirements, calculating a match score and identifying strengths and gaps
"""
inputs = { candidate_profile = "CandidateProfile", job_requirements = "JobRequirements" }
output = "CandidateMatch"
model = "$writing-factual"
system_prompt = """
You are an expert HR analyst specializing in candidate-job fit evaluation. Your task is to produce a structured match analysis comparing a candidate's profile against job requirements.
"""
prompt = """
Analyze how well the candidate matches the job requirements. Evaluate their fit by comparing their skills, experience, and qualifications against what the position demands.

@candidate_profile

@job_requirements

Provide a comprehensive match analysis including a numerical score, identified strengths, gaps, and an overall assessment.
"""

View the pipeline flowchart:

flowchart LR
    %% Pipe and stuff nodes within controller subgraphs
    subgraph sg_n_8b2136e3fe["batch_analyze_cvs_for_job_offer"]
        subgraph sg_n_91d5d6dc7c["prepare_job_offer"]
            n_fde22777cb["analyze_job_requirements"]
            s_f9f703fbb4(["job_requirements<br/>JobRequirements"]):::stuff
            n_b8469c838f["extract_one_job_offer"]
            s_d998350046(["job_offer_pages<br/>Page"]):::stuff
        end
        subgraph sg_n_f8d5afb7cd["process_cv_batch"]
            subgraph sg_n_6e53e16369["process_cv"]
                n_c18aded200["analyze_match"]
                s_5c911f7e54(["match_analysis<br/>CandidateMatch"]):::stuff
                n_a7ed00ac24["analyze_one_cv"]
                s_c5ae714e89(["candidate_profile<br/>CandidateProfile"]):::stuff
                n_d24f39aa60["extract_one_cv"]
                s_427beb5195(["cv_pdf<br/>Document"]):::stuff
                s_f1f80289df(["cv_pages<br/>Page"]):::stuff
            end
            subgraph sg_n_2cfb7a32c8["process_cv"]
                n_f6a25d1769["analyze_match"]
                s_ea99eee6ed(["match_analysis<br/>CandidateMatch"]):::stuff
                n_f48b73fbee["analyze_one_cv"]
                s_e1ffee913e(["candidate_profile<br/>CandidateProfile"]):::stuff
                n_d16f2fe381["extract_one_cv"]
                s_041bb18fb4(["cv_pdf<br/>Document"]):::stuff
                s_5fbba7194a(["cv_pages<br/>Page"]):::stuff
            end
            subgraph sg_n_08a7186be9["process_cv"]
                n_937e750ea4["analyze_match"]
                s_bb41a103f0(["match_analysis<br/>CandidateMatch"]):::stuff
                n_786a2969d5["analyze_one_cv"]
                s_c47fe821d7(["candidate_profile<br/>CandidateProfile"]):::stuff
                n_38f0cfd11c["extract_one_cv"]
                s_2634ece93d(["cv_pdf<br/>Document"]):::stuff
                s_44e253b325(["cv_pages<br/>Page"]):::stuff
            end
        end
    end

    %% Pipeline input stuff nodes (no producer)
    s_9b7e74ac51(["job_offer_pdf<br/>Document"]):::stuff

    %% Data flow edges: producer -> stuff -> consumer
    n_a7ed00ac24 --> s_c5ae714e89
    n_b8469c838f --> s_d998350046
    n_f48b73fbee --> s_e1ffee913e
    n_d16f2fe381 --> s_5fbba7194a
    n_fde22777cb --> s_f9f703fbb4
    n_d24f39aa60 --> s_f1f80289df
    n_38f0cfd11c --> s_44e253b325
    n_786a2969d5 --> s_c47fe821d7
    n_c18aded200 --> s_5c911f7e54
    n_f6a25d1769 --> s_ea99eee6ed
    n_937e750ea4 --> s_bb41a103f0
    s_c5ae714e89 --> n_c18aded200
    s_9b7e74ac51 --> n_b8469c838f
    s_d998350046 --> n_fde22777cb
    s_e1ffee913e --> n_f6a25d1769
    s_427beb5195 --> n_d24f39aa60
    s_041bb18fb4 --> n_d16f2fe381
    s_2634ece93d --> n_38f0cfd11c
    s_5fbba7194a --> n_f48b73fbee
    s_f9f703fbb4 --> n_c18aded200
    s_f9f703fbb4 --> n_f6a25d1769
    s_f9f703fbb4 --> n_937e750ea4
    s_f1f80289df --> n_a7ed00ac24
    s_44e253b325 --> n_786a2969d5
    s_c47fe821d7 --> n_937e750ea4

    %% Batch edges: list-item relationships
    s_52d84618d0(["match_analyses<br/>CandidateMatch"]):::stuff
    s_5c911f7e54 -."[0]".-> s_52d84618d0
    s_ea99eee6ed -."[1]".-> s_52d84618d0
    s_bb41a103f0 -."[2]".-> s_52d84618d0

    %% Style definitions
    classDef failed fill:#ffcccc,stroke:#cc0000
    classDef stuff fill:#fff3e6,stroke:#cc6600,stroke-width:2px
    classDef controller fill:#e6f3ff,stroke:#0066cc

    %% Subgraph depth-based coloring
    style sg_n_08a7186be9 fill:#fffde6
    style sg_n_2cfb7a32c8 fill:#fffde6
    style sg_n_6e53e16369 fill:#fffde6
    style sg_n_8b2136e3fe fill:#e6f3ff
    style sg_n_91d5d6dc7c fill:#e6ffe6
    style sg_n_f8d5afb7cd fill:#e6ffe6

Run Your Method

Via CLI:

pipelex run bundle cv_batch_screening.mthds --inputs inputs.json

Create an inputs.json file with your PDF URLs:

{
  "cvs": {
    "concept": "native.Document",
    "content": [
      { "url": "https://pipelex-web.s3.amazonaws.com/demo/John-Doe-CV.pdf" },
      { "path": "inputs/Jane-Smith-CV.pdf" }
    ]
  },
  "job_offer_pdf": {
    "concept": "native.Document",
    "content": {
      "url": "https://pipelex-web.s3.amazonaws.com/demo/Job-Offer.pdf"
    }
  }
}

Via Python:

import asyncio
from pipelex.core.stuffs.document_content import DocumentContent
from pipelex.pipelex import Pipelex
from pipelex.pipeline.runner import PipelexRunner
# Generated by: `pipelex build structures bundle cv_batch_screening.mthds`
from structures.cv_batch_screening__candidate_match import CandidateMatch

async def run_pipeline() -> list[CandidateMatch]:
    runner = PipelexRunner()
    response = await runner.execute_pipeline(
        pipe_code="batch_analyze_cvs_for_job_offer",
        inputs={
            "cvs": {
                "concept": "Document",
                "content": [
                    DocumentContent(url="https://pipelex-web.s3.amazonaws.com/demo/John-Doe-CV.pdf"),
                    DocumentContent(path="inputs/Jane-Smith-CV.pdf"),
                ],
            },
            "job_offer_pdf": {
                "concept": "native.Document",
                "content": DocumentContent(url="https://pipelex-web.s3.amazonaws.com/demo/Job-Offer.pdf"),
            },
        },
    )
    pipe_output = response.pipe_output
    print(pipe_output)
    return pipe_output.main_stuff_as_items(item_type=CandidateMatch)

Pipelex.make()
asyncio.run(run_pipeline())

What is Pipelex?

Pipelex is the reference Python runtime for executing AI methods defined in the MTHDS open standard. It separates what a method does from how it runs — you declare intent, the runtime handles execution.

MTHDS is a typed, declarative language built on two primitives:

• Concepts — semantically typed data, named after real domain things (ContractClause, CandidateProfile, Invoice)
• Pipes — typed transformations with explicit inputs and outputs (LLM calls, extraction, image generation, branching, batching)

Methods are readable by domain experts, executable by agents, versionable in Git, and portable across runtimes. The .mthds format is TOML-based — no framework lock-in, no boilerplate.

The sweet spot between code and agent skills:

	Code	MTHDS	Agent Skills
Control	Total control, total effort	Structured freedom, open standard	Total freedom, no guarantees
Time to production	Days, 80% boilerplate	Minutes, zero boilerplate	Minutes, different result every run
Validation	Deterministic, testable	Typed schemas, validated before runtime	No validation, no audit trail
Audience	Developers only	Engineers and domain experts	Anyone

Agent-first by design: The Claude Code plugin lets agents write, edit, run, and compose methods. A domain expert who can describe what they need in plain language can have Claude author the method, which then runs consistently, is testable, and lives in version control.

The MTHDS Ecosystem

	Description	Link
MTHDS Standard	The open standard specification — language, package system, and typed concepts	mthds.ai
MTHDS Hub	Discover and share methods — browse packages, search by signature	mthds.sh
Skills Plugin	Claude Code plugin — 11 commands to build, run, edit, check, fix, and publish methods	github.com/mthds-ai/skills
Package System	Versioned dependencies, lock files with SHA-256 integrity, cross-package references via ->	Packages docs
Know-How Graph	Typed discovery — "I have X, I need Y" — find methods or chains by typed signature	Know-How Graph

Skills Plugin Commands

Command	Description
/mthds-build	Build new AI method bundles from scratch
/mthds-run	Execute methods and interpret their JSON output
/mthds-edit	Modify existing methods — change pipes, update prompts, add steps
/mthds-check	Validate bundles for issues (read-only)
/mthds-fix	Auto-fix validation errors
/mthds-explain	Walk through execution flow in plain language
/mthds-inputs	Prepare inputs: templates, synthetic data, user files
/mthds-install	Install method packages from GitHub or local dirs
/mthds-pkg	Package management — init, deps, lock, install, update
/mthds-publish	Publish methods to the hub
/mthds-share	Share methods on social media

See Pipelex in Action

Claude Code builds your AI Method

IDE Extension

We highly recommend installing our extension for .mthds syntax highlighting in your IDE:

• VS Code: Install from the VS Code Marketplace
• Cursor, Windsurf, and other VS Code forks: Install from the Open VSX Registry, or search for "Pipelex" directly in your extensions tab

Running pipelex init will also offer to install the extension automatically if it detects your IDE.

Examples & Cookbook

Explore real-world examples in our Cookbook repository:

Clone it, fork it, and experiment with production-ready methods for various use cases.

Run Anywhere

The same .mthds file runs from multiple execution targets:

Target	How
CLI	pipelex run bundle method.mthds --inputs inputs.json
Python	PipelexRunner().execute_pipeline(...)
REST API	Self-hosted API server
MCP	Model Context Protocol — agents call methods as tools
n8n	Pipelex node for workflow automation

Optional Features

The package supports the following additional features:

• anthropic: Anthropic/Claude support for text generation
• google: Google models (Vertex) support for text generation
• mistralai: Mistral AI support for text generation and OCR
• bedrock: Amazon Bedrock support for text generation
• fal: Image generation with Black Forest Labs "FAL" service
• linkup: Web search with Linkup
• docling: OCR with Docling

Install all extras:

pip install "pipelex[anthropic,google,google-genai,mistralai,bedrock,fal,linkup,docling]"

Privacy & Telemetry

Pipelex supports two independent telemetry streams:

• Gateway Telemetry: When using Pipelex Gateway, telemetry must be enabled (tied to your hashed API key) to monitor service quality and enforce fair usage. Learn more
• Custom Telemetry: User-controlled via .pipelex/telemetry.toml for your own observability systems (Langfuse, PostHog, OTLP). Learn more

We only collect technical data (model names, token counts, latency, error rates) — never your prompts, completions, or business data. Set DO_NOT_TRACK=1 to disable all telemetry (note: Gateway requires telemetry to function).

For more details, see the Telemetry Documentation or read our Privacy Policy.

Contributing

We welcome contributions! Please see our Contributing Guidelines for details on how to get started, including development setup and testing information.

Join the Community

Join our vibrant Discord community to connect with other developers, share your experiences, and get help with your Pipelex projects!

Support

• GitHub Issues: For bug reports and feature requests
• Discussions: For questions and community discussions
• Documentation

Star Us!

If you find Pipelex helpful, please consider giving us a star! It helps us reach more developers and continue improving the tool.

License

This project is licensed under the MIT license. Runtime dependencies are distributed under their own licenses via PyPI.

---

"Pipelex" is a trademark of Evotis S.A.S.

© 2026 Evotis S.A.S.