Open source runtime. Managed platform on top.
Start free with the OSS runtime and core integrations. Add the managed platform when you need it in production.
Pipelex Open Source
Free forever · MIT-licensed
The open standard, the reference runtime, and open integrations to ship anywhere.
BUILD
- Methods Language - the MTHDS open standard
- VS Code Extension
- ◦Semantic coloring, linting, formatting, contextual error messages
- ◦Interactive flowchart visualization
- Plugins with skills & CLIs for Claude Code and Codex
RUN
- Methods execution runtime — library, CLI, REST API
- Client SDKs — Python, TypeScript
INTEGRATIONS
- Automations: n8n node (OSS + cloud)
- Observability: Langfuse, PostHog, OpenTelemetry
INFERENCE
- Bring your own keys — 17+ providers
- Local inference (Ollama, any OpenAI-compatible server)
Pipelex Business
Contact sales
The managed platform on top of the OSS runtime — for teams running Pipelex in production.
BUILD
- Pipelex Studio
- ◦Web app: build with our agent
- ◦MCP: build in ChatGPT, Codex, Claude Cowork
- ◦Share methods securely within teams
- ◦1-click Deploy as an agent tool, API endpoint, or mini-app
RUN
- Control & Conformance
- ◦Fully configurable and extensible by IT
- ◦Automated testing, validation, CI/CD
- Workflow orchestration
- ◦Plugins for Temporal and Mistral Workflows
- Pipelex Cloud
- ◦Durable workflows on our hosted cloud
- Managed hosting on AWS, GCP, or AzureComing soon
- Methods OptimizerComing soon
- ◦Optimize for performance, cost, and ESG
INFERENCE
- Pipelex Gateway
PREMIUM SUPPORT
- P0 response within 12 business hours
- 1 hour/month of dedicated 1:1 support
Everything you need to run AI in production.
Simple to build. Durable when it runs. Governed end to end.
Ready to build, robin?
describe a pipeline · the assistant scaffolds the pipes · you run it
Ship AI without breaking a sweat
You want to nail your use case. Instead you're stuck in a dev cycle, back and forth between prompt and code, transcribing business logic by hand.
Build in natural language in Pipelex Studio, or using our MCP plugin inside your favorite agent: Claude Code/Cowork, Codex, Mistral Vibe... Then deploy in one click as an agent tool, API endpoint, or mini-app. Share methods securely across your team.
Runs that survive the real world
APIs time out, models rate-limit, a job dies at step 23 of 25. Restart from zero, and you pay for those 22 steps of inference twice.
Durable execution persists state, retries on failure, and resumes exactly where it left off. It scales horizontally from 5 documents to 5,000. We provide native plugins for Temporal and Mistral Workflows, so you can build your own infrastructure, or you can run it all on Pipelex Cloud.
How durable execution works →
One gateway for every model
AI model providers each come with separate contracts, separate keys, separate bills, and no single view of cost or usage.
Pipelex Gateway delivers premium and specialized inference, including OCR, through one bill, one key, one place to govern. Route the right model to each task with a simple configuration file, collect detailed usage & cost reports anyway you like.
See every run and get help fast
When a run misbehaves in production, you need to see exactly what happened. And when it's urgent, a community forum isn't an answer.
Full tracing and observability through Langfuse, OpenTelemetry, and PostHog. Plus premium support: P0 response within 12 business hours and a dedicated hour each month of 1:1 time with the people who build Pipelex.
We deploy 3 AI automations on your infrastructure in 3 weeks.
Fixed-price Pipelex AI Sprint. Contract-backed reliability threshold. Code is yours.
Add AI methods to Claude Code in minutes
Install. Define. Execute. No boilerplate, no configuration, no lock-in.
Install mthds: run bash -c 'npm install -g mthds && mthds-agent bootstrap && claude plugin marketplace add mthds-ai/mthds-plugins && claude plugin install mthds@mthds-plugins'. Then tell me to /reload-plugins.
npm install -g mthds mthds-agent bootstrap claude plugin marketplace add mthds-ai/mthds-plugins claude plugin install mthds@mthds-plugins
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.
Yes — the Pipelex AI Sprint is a fixed-price, 3-week engagement to ship three automations on your infrastructure. €20,000 (excl. VAT), contract-backed reliability threshold, and a 20% fee reduction if we miss it. See the Sprint section for the full offer.
You walk away with code, methods, and a Docker image — yours. Three paths from there: run it autonomously, keep an Extended Pipelex Support contract (monthly), or migrate to Pipelex Cloud when it launches. Sprint clients get priority access to Pipelex Cloud.
Heads of AI, AI Engineering leads, and COOs in regulated or sensitive environments — banking, insurance, capital markets/PE, freelance platforms — who need repeatability, handle document volume, want to keep control of the code, and can’t afford a 6-month build cycle.