Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

LangChain.js

LangChain.js, which includes an optional TypeSafeClassifier runnable and middleware for bounded routing and tool-call checks with Jev.

PluginproductionMIT
View on GitHub ↗

Overview

LangChain.js is the JavaScript and TypeScript version of the LangChain framework for building LLM-powered applications and agents, with a standard interface for models, embeddings, vector stores and many integrations, plus Deep Agents and LangGraph.js for orchestration and LangSmith for monitoring.

Per the listings, it includes an optional Jev integration: a TypeSafeClassifier runnable that sends state and predefined questions to Jev, and middleware for bounded routing and tool-call checks. The README excerpt is the framework's general overview and does not describe this integration, so its exact API is not confirmed here. It mirrors the Python LangChain integration and lets JavaScript developers drop typed decisions into existing chains and agents.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich route should this request take? (routing middleware)(inferred)—
Yes / noShould this tool call be allowed? (tool-call check)(inferred)—
ChoiceUser-defined classification via TypeSafeClassifier—

How it works

  1. Add the TypeSafeClassifier runnable or middleware
  2. Runnable sends state and predefined questions to Jev
  3. Typed answers drive routing or tool-call checks
  4. Chain or agent continues

Strengths

  • Native integration in a major JS agent framework
  • Mirrors the Python integration
  • Middleware for common harness roles

Caveats

  • Integration details not in the main README
  • Optional; requires a TypeSafe key

Getting started

npm install langchain; see LangChain.js integration docs for the TypeSafe classifier.

At a glance

Type
Plugin
Status
production
Language
TypeScript
Runtime
Node and browser
Has code
yes
Has tests
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • An optional LangChain.js TypeSafeClassifier integration for sending state and predefined questions to Jev.

    logicrw/awesome-jev-projects

  • JavaScript/TypeScript classifier Runnable and middleware for bounded routing and tool-call checks.

    cobanov/awesome-jev

Frequently asked questions

How does LangChain.js use Jev?

Through an optional TypeSafeClassifier runnable and middleware for routing and tool-call checks, per the listings.

Is there a Python equivalent?

Yes, LangChain's Python package has a similar integration.

Is it required?

No, it is optional.

Related projects

  • LangChain

    LangChain's Python framework, which includes an optional TypeSafeClassifier runnable plus model-routing and risky-tool middleware using Jev.

    PluginproductionPython
  • Building a Harness with Jev

    LangChain blog guide on wiring Jev into an agent harness as a dangerous-action classifier and model router.

    Articlediscussion
  • Composio

    Composio agent SDK with an optional TypeSafe provider that uses Jev to shortlist and pick tools and closed-set arguments.

    ProjectproductionTypeScript
  • claude-jev-mod

    Claude Code mod that adds $.jev to the engine interface so other plugins and hooks can ask Jev typed questions through six providers.

    ServicebetaTypeScript
  • effect-agent

    Yielded Agent: durable Effect agent threads in TypeScript, listed for a TypeSafe decision provider for typed question sets.

    ProjectbetaTypeScript
  • eve

    Vercel's filesystem-first agent framework, whose experimental evaluate and autoModel paths default to Jev via AI Gateway.

    ServicebetaTypeScript