Skip to content
Plugin for Claude Code

Executable AI Methods

Pipelex is the reference runtime for [MTHDS]

[MTHDS]A typed, declarative language to define AI workflows as reusable, versionable files — readable by humans, executable by agents.

No boilerplate, no lock-in.

pip install pipelex
Copied to clipboard!

When agents automate business tasks, they're stuck between Writing Code and Writing Agent Skills

Code gives you control but takes weeks.

Agent Skills take minutes but give you no guarantees.

Business automation deserves better than this tradeoff.

The sweet spot
More controlMore freedom

Code

Total control. Total effort.

.mthds

MTHDS

Structured freedom. Open standard.

Agent Skills

Total freedom. No guarantees.

MTHDS is an open standard for declarative AI methods. Pipelex is its reference runtime — readable like instructions, reliable like code, ready in hours instead of weeks.

From business logic to executable method

Define methods in declarative .mthds files. Version them in Git. Run them with one command.

hr_screening.mthds
HR Screening Pipeline — screen_candidates execution flow with batch CV evaluation and conditional routing
domain = "hr_screening"
description = "Analyze a job offer to build a scorecard, batch process CVs"
main_pipe = "screen_candidates"

# ── Concepts ──────────────────────────────────────────────

[concept.Criterion]
description = "A single evaluation criterion for scoring candidates"

[concept.Criterion.structure]
name = {type = "text", required = true}
description = {type = "text", required = true}
weight = {type = "number", description = "Importance 1-10", required = true}

[concept.Scorecard]
description = "Evaluation scorecard built from a job offer"

[concept.Scorecard.structure]
job_title = {type = "text", required = true}
company = {type = "text"}
required_skills = {type = "list", item_type = "text"}
criteria = {type = "list", item_type = "concept", item_concept_ref = "hr_screening.Criterion"}

[concept.CvEvaluation]
description = "Complete evaluation of a candidate CV"

[concept.CvEvaluation.structure]
candidate_name = {type = "text", required = true}
overall_score = {type = "number", required = true}
fit = {type = "text", required = true, choices = ["yes", "no"]}
strengths = {type = "list", item_type = "text"}
weaknesses = {type = "list", item_type = "text"}

# ── Main Pipe ─────────────────────────────────────────────

[pipe.screen_candidates]
type = "PipeSequence"
inputs = {job_offer = "Document", cvs = "Document[]"}
output = "CvResult[]"
steps = [
    {pipe = "extract_job_offer", result = "job_pages"},
    {pipe = "build_scorecard", result = "scorecard"},
    {pipe = "evaluate_cv", batch_over = "cvs", result = "results"},
]

[pipe.build_scorecard]
type = "PipeLLM"
inputs = {job_pages = "Page[]"}
output = "Scorecard"
model = "$writing-factual"
prompt = """Analyze this job offer and build a scorecard..."""

[pipe.evaluate_cv]
type = "PipeSequence"
inputs = {cv = "Document", scorecard = "Scorecard"}
output = "CvResult"
steps = [
    {pipe = "extract_cv", result = "cv_pages"},
    {pipe = "score_cv", result = "evaluation"},
    {pipe = "route_by_fit", result = "cv_result"},
]

[pipe.score_cv]
type = "PipeLLM"
inputs = {cv_pages = "Page[]", scorecard = "Scorecard"}
output = "CvEvaluation"
prompt = """Score the candidate on EACH criterion..."""

# ── Conditional Routing ───────────────────────────────────

[pipe.route_by_fit]
type = "PipeCondition"
inputs = {evaluation = "CvEvaluation", scorecard = "Scorecard"}
output = "CvResult"
expression = "evaluation.fit"

[pipe.route_by_fit.outcomes]
yes = "handle_fit"
no = "handle_rejection"
Drag to explore
Method Definition
Pipeline Execution21/2131.84s

Build. Package. Run. Observe.

One method. Any model. Anywhere.

Build

Author methods in the MTHDS open standard. Readable by engineers and domain experts alike.

Combine the perfect model for each task

LLMsOCRImage GenerationVoiceSmall ModelsLocal Models
Declarative .mthds language

Concepts for typed data, pipes for transformations — 5 operator types and 4 controllers built into the language

Typed concepts with refinement

Data schemas with full type safety, structured outputs, and concept refinement hierarchies

Agent-authored

Agents can write, edit, compose, and discover methods via typed signatures autonomously

Every AI Model, One Pipeline

Chain LLMs, OCR engines, and image generators from any provider in a single method. Always pick the best model for each task — that's how Claude Code uses Pipelex to read scanned PDFs and generate images.

Language ModelsClaudeGPT-4oGeminiGrokDeepSeekMistralLlama
Document IntelligenceAzure Doc IntelligenceDeepSeek OCRDocling
Image GenerationNano Banana ProGPT-Image-1.5

Gateway

Instant access to every major provider through a single endpoint

Bring Your Own Keys

Use your existing API keys from any provider — full control, zero markup

Local / Self-hosted

Run models on your own infrastructure with Ollama or any OpenAI-compatible server

Pipelex Cloud

Coming Soon

Managed infrastructure, team workspaces, and built-in observability — so you can focus on methods, not ops.

Join the Waitlist

Built for repeatable business automation

Deterministic AI methods for knowledge work that demands consistent results at scale.

Invoice Processing

Extract structured data from invoices, validate against schemas, and push to your systems.

3 weeks to production

Document Analysis

Analyze contracts, reports, and documents with consistent extraction methods.

Targeting 99% accuracy

Email Automation

Classify, route, and respond to emails with repeatable AI methods.

Minutes to set up

Content Generation

Generate marketing copy, product descriptions, and reports at scale.

1 day to onboard

Compliance Review

Automated compliance checking with audit trails and version control.

Every step traced

What early adopters say

Teams already using Pipelex in production.

Adrien Vesteghem

We're pushing toward 99% accuracy—the threshold where real automation becomes possible. Pipelex gives us the rigor to get there.

Adrien Vesteghem·Chief AI Officer, Meilleurtaux
Yannick Tian

I can set up a clear method in minutes and actually see what's happening. No more black-box prompts or guessing what went wrong.

Yannick Tian·Staff AI Engineer, Gojob
Aurélien Violette

Pipelex took us from idea to production in just three weeks. It's so simple that even our intern was up and running in two days.

Aurélien Violette·CTO, Beink Dream

Frequently Asked Questions

Everything you need to know about Pipelex and how it works.

Agents need a format they can reliably generate and execute — not free-form code. .mthds files are declarative, deterministic, and portable: agents write them, humans review them, Pipelex runs them. Python stays in the runtime; the method definition stays agent-readable.

MTHDS is an open standard for defining, packaging, and distributing AI methods. It has two pillars: the Language (typed concepts, pipes, and domains in .mthds files) and the Package System (versioned dependencies, lock files, cross-package references, and a federated registry at mthds.sh). The standard is maintained at mthds.ai and anyone can implement a runtime. Pipelex is the reference implementation.

Yes. MTHDS is an open standard with a public specification, not a proprietary format. Any platform can parse .mthds files, validate typed signatures, and execute methods. Pipelex is the reference runtime, but the standard is designed for broad adoption — your methods are never locked to a single tool.

Those are code-first frameworks with proprietary formats — humans write Python or TypeScript. Pipelex implements the MTHDS open standard: a portable, typed language with a real package system. Your methods aren't locked to any runtime.

GUI-based platforms lock methods in their ecosystem. MTHDS methods are plain-text files — version them in Git with semantic versioning, compose them across packages with cross-package references, deploy them anywhere.

No. Pipelex provides deterministic methods that agents call as tools via MCP or API. We make agents reliable at repeatable business tasks — we don't replace your agent stack.

Repeatable, deterministic AI tasks: invoice processing, contract analysis, report generation, compliance review. If it needs consistent results at scale, Pipelex fits. Not designed for creative exploration or open-ended tasks.

Fully. The MTHDS standard and Pipelex runtime are MIT-licensed. The open-core model means enterprise features (managed cloud, advanced observability, certification) are commercial, but the runtime and the standard stay open.

Backed by

21stStation FGoogle for StartupsAWSFounder Program
Open source·MIT License·...

Run your first method in 5 minutes

Install. Define. Execute. No boilerplate, no configuration, no lock-in.

npx skills add mthds-ai/skills