The production agent IDE Canvas · Code · Export · Deploy — one desktop app

Design agents visually.
Ship to production.

The production agent IDE — drag-and-drop canvas, asset designers, RAG pipelines, and multi-language project generation. Python on PyPI and Spring AI on Maven Central ship today; Go and Rust targets are expanding. LangTailor supports two project types: Agentic Development (graphs, skills, deploy) and Plugin Creator (multi-platform packs). Use langstitch plugin new and langstitch pack to build .langstitch-pack.zip artifacts (validation is fail-closed unless you pass --allow-partial). Browse personas, prompts, and packs in the marketplace.

Download LangTailor (Windows & macOS) Open VSX GitHub
LangTailor v0.3.1 Python · PyPI Spring AI · Maven Central Go · Rust expanding MIT
Download

LangTailor desktop IDE

Full agent IDE — canvas, code, terminal, git, platform ops, marketplace, multi-language export.

All releases →

Windows x64 installer

LangTailor-0.3.2-win-x64-setup.exe
v0.3.1
Download

macOS arm64

DMG · Apple Silicon
v0.3.1
Download

macOS x64

DMG · Intel
v0.3.1
Download

Install notes

  • Windows: Run the setup.exe installer and launch LangTailor from the Start menu.
  • macOS: Open the DMG and drag LangTailor to Applications. If Gatekeeper blocks an unsigned DMG, Right-click → Open, then confirm Open.
  • VS Code / VSCodium: Install from Open VSX, or run codium --install-extension langstitch.langtailor-canvas (swap codium for code in VS Code).

github.com/LangStitch/langtailor-releases · github.com/LangStitch/langtailor

Marketplace

82 catalog items ready to sync

Live catalog from api.langstitch.com · GitHub sign-in · sync into canvas · publish / review at marketplace.langstitch.com

Open marketplace →
20connectors 8agents 28graphs 16MCP packs 10plugins
Choose your install

Two ways to build with LangStitch

Same canvas, same *.langstitch.json projects — pick the VS Code extension for a focused editor workflow, or LangTailor IDE for advanced control from design through deploy.

LangTailor Canvas · VSX

For VS Code

The full LangStitch graph editor inside VS Code or VSCodium — design agents and export production code without switching tools.

Canvas · designers · marketplace · export

  • Visual LangGraph canvas with LLM, RAG, Tool, Agent nodes
  • In-canvas marketplace — browse and sync connectors, graphs, and MCP packs
  • Canvas toolbar with Build / Export and marketplace actions
  • Offline export — production Python projects without a cloud account
  • Asset designers — skills, guardrails, personas, RAG pipelines
  • Production export — Python from the IDE today; Spring AI via the langstitch-spring-ai CLI on Maven Central. Go and Rust expanding.
  • One-click install from Open VSX — stays in your editor flow
Install from Open VSX Download VSIX v0.3.1 
codium --install-extension langstitch.langtailor-canvas

LangTailor IDE

Full control

The purpose-built agent IDE — everything in VSX, plus advanced tooling to run, debug, and ship agents in your language of choice.

Canvas · code · terminal · platform · deploy

  • Everything in the VSX canvas extension
  • Canvas + code views kept in sync — edit either side
  • Integrated terminal, git SCM, and language tooling (Python LSP today)
  • Local Build / Run / Test / Debug / Deploy from one panel
  • Platform panel — Docker build, Helm deploy, eval runs
  • Marketplace sign-in and plugin sync built in
  • Export from canvas — Python projects in one step; Spring AI needs the Java CLI (langstitch-spring-ai compile). Go and Rust expanding.
Download LangTailor (Windows & macOS) v0.3.1
Start with VSX, grow into IDE anytime. Projects are identical — open the same *.langstitch.json files in LangTailor when you want terminal, git, platform ops, or marketplace without migrating or re-exporting. Download LangTailor →
Release history

Versioned releases

Features

LangTailor IDE — beyond the canvas

Component Designer, asset designers, MCP Studio, marketplace, IR v2 documents with SDK compile, and a local Build / Run / Test / Debug / Deploy toolchain — with A2A and human-in-the-loop where your graphs need them.

01

Canvas + code

Graph and source stay in sync — edit either side without context switching.

LLMToolAgentRAGSubgraph
02

Component Designer

Custom nodes, connectors, adaptors — export as .component.json for marketplace.

03

Asset designers

Skills, guardrails, personas, RAG pipelines — vector / hybrid retrieval.

04

MCP Studio + integrations

MCP Studio, tool registry, remote graphs, A2A, and human-in-the-loop (HITL) interrupts.

05

Local Build / Run / Test / Debug / Deploy

Day-to-day toolchain on your machine — plus Docker and Helm when you are ready to ship.

06

Multi-language export

Python on PyPI and Spring AI on Maven Central — Go and Rust expanding. Same canvas, same project layout.

07

Marketplace

82 items — 20 connectors · 8 agents · 28 graphs · 16 MCP packs · 10 plugins. Sign in once; sync into the IDE.

08

Platform ops

Terminal, git SCM, Docker build, Helm deploy, and eval runs from one desktop app.

Contact

Business & training

Enterprise rollouts, team training, LangGraph workshops, and partnership inquiries — email us and we will follow up.

connect@langstitch.com

Business · training · workshops · partnerships

Privacy: If you accept analytics cookies we record pages viewed, device/browser details, and approximate location (from IP) in our database. Decline to opt out. Email connect@langstitch.com for data requests.

Privacy

Analytics & cookies

How LangStitch uses first-party analytics on this site.

Overview

LangStitch runs first-party analytics on our public sites to understand how visitors use pages and features. We do not use third-party ad trackers or sell visitor data.

What we collect (with consent)

  • Pages viewed, clicks, scroll depth, and time on page
  • Browser, operating system, device type, screen size, and language
  • Approximate location (country/region/city derived from IP)
  • Referrer, UTM campaign parameters, and landing URL
  • A random visitor ID stored in your browser (local storage) and a session ID (session storage)

Your choices

Accept or decline analytics in the cookie banner. If you decline, we do not set tracking cookies or record browsing events. You can clear site data in your browser to reset your choice.

Data requests

Email connect@langstitch.com to ask about your data or request deletion.

Last updated: July 2026