ByteZone
Back to listClaim this project

PipelexDeveloper tools

pipelex

Declarative language and runtime for composable AI workflows

  • Automation
  • CLI
  • IDE plugin
  • Windows
  • macOS
  • Linux
  • Self-hostable
  • Runs locally
Open websiteView on GitHub
pipelex screenshot
Popularity
851 Stars
GitHub stars
Recent activity
9/12/2026
Updated in the last 30 days
License
MIT
Permissive

Why it matters

We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.

Last 90 days

Problem

Building AI workflows often suffers from scattered prompts, lack of typed structures, and tedious model integration.

Practical value

Provides declarative .mthds configuration, type checking, batch processing, and VS Code flowchart visualization to improve workflow development.

Innovation / differentiation

Introduces a strongly typed declarative DSL around Methods and integrates directly into Claude Code and Codex agent commands.

Leverage potential

Abstracting away differences across 60+ models and local LLMs allows running declared methods across providers without rewriting logic.

Why now

With the rapid rise of AI agents executing multi-step tasks, structured and declarative workflow DSLs align well with developer needs.

Community activity

In the last 90 days there were 1 new issues and 202 pull requests; the bounded issue/PR samples include 1 issue authors and 2 PR contributors, with at least 32 releases.

Maintainer responsiveness

The 1-issue window sample had a 0% close rate, and the 100-pull-request sample had a 86% merge rate. Maintainer-comment observations covered only 100% of that issue sample, so response rate and first-response speed are not reported.

2 contributors in PR sampleAt least 32 releasesPR merge rate 86% · 100 sampled in window

Key highlights

  • Declarative Syntax: Define inputs, outputs, and prompts in .mthds files
  • Typed Inputs & Outputs: Enforce schemas using semantic concept definitions
  • Composable Pipelines: Combine sequences, nested methods, and batch operations

Quick start

How it is installed, how hard it is, and where to start.

Self-hostableRuns locally

Best for

  • Teams that want data on their own servers
  • Developers who want to try it on their machine

More about it

Pipelex is an open-source framework for building reusable, strongly-typed AI workflows. Developers declare execution steps in .mthds files, while Pipelex handles provider routing, structured parsing, and pipeline state. It integrates into CLI workflows and coding assistants like Claude Code and Codex.

Sources

Each field shows its status and source — expand to review.

13 · Expand

  • capability tags

    Verified

    automation

    Source: admin_cms · cms editor · 9/14/2026

  • editor note

    Verified

    {"en":"Pipelex uses .mthds files to structure LLM tasks with explicit types and inputs. It turns prompt chains into versionable, reproducible procedures that integrate with coding agents.","zh":"Pipelex 引入了 .mthds 配置文件格式，通过定义显式类型、输入输出和步骤关系，让复杂的 LLM 工作流变得可维护和可复用。它支持将多步 AI 流程与主流 Coding Agent 结合使用。"}

    Source: admin_cms · cms editor · 9/14/2026

  • intro

    Verified

    {"en":"Pipelex is an open-source framework for building reusable, strongly-typed AI workflows. Developers declare execution steps in .mthds files, while Pipelex handles provider routing, structured parsing, and pipeline state. It integrates into CLI workflows and coding assistants like Claude Code and Codex.","zh":"Pipelex 是一种用于构建可复用、强类型 AI 方法的开源框架。用户可以通过 .mthds 描述文件将复杂提示词逻辑拆分为确定性的执行步骤。框架负责底层的模型调度、数据解析与结果传递，支持在终端命令行或 Claude Code、Codex 等 AI 开发代理中快速调用。"}

    Source: admin_cms · cms editor · 9/14/2026

  • Latest release

    Verified

    v0.57.0

    Source: GitHub API · latest_release=v0.57.0 · 9/14/2026

  • License

    Verified

    MIT

    Source: GitHub API · license.spdx_id=MIT · 9/14/2026

  • needs api key

    Verified

    No

    Source: admin_cms · cms editor · 9/14/2026

  • One-liner

    Verified

    {"en":"Declarative language and runtime for composable AI workflows","zh":"声明式 AI 工作流开发工具与语法规范"}

    Source: admin_cms · cms editor · 9/14/2026

  • Platforms

    Verified

    windows, macos, linux

    Source: admin_cms · cms editor · 9/14/2026

  • Category hint

    Inferred from materials

    ai-apps

    Source: Project README · hint=ai-apps · 8/24/2026

  • product forms

    Verified

    cli, ide_plugin

    Source: admin_cms · cms editor · 9/14/2026

  • role tags

    Verified

    Source: admin_cms · cms editor · 9/14/2026

  • supports local

    Verified

    Yes

    Source: admin_cms · cms editor · 9/14/2026

  • supports self host

    Verified

    Yes

    Source: admin_cms · cms editor · 9/14/2026

Related projects

Other verified projects matched by category, capabilities, and intended roles.

playwright

A cross-browser automation framework for testing and AI agent control, supporting Chromium, Firefox, and WebKit.

Same Developer tools categoryBoth support Automation

puppeteer

A JavaScript library that provides a high-level API to control Chrome or Firefox over DevTools Protocol or WebDriver BiDi.

Same Developer tools categoryBoth support Automation

container

Apple’s command-line tool for running OCI Linux containers as lightweight virtual machines on Apple silicon Macs.

Same Developer tools categoryBoth support Automation

compose

Docker’s official CLI tool for defining and running multi-container applications from a Compose file.

Same Developer tools categoryBoth support Automation

WSL

Windows Subsystem for Linux allows you to run Linux command-line tools and applications directly on Windows without the overhead of a traditional virtual machine.

Same Developer tools categoryBoth support Automation

openai-agents-python

A Python framework by OpenAI for building multi-agent workflows, supporting text, voice, and sandbox-based agent applications.

Same Developer tools categoryBoth support Automation