How is this different from routing with Claude or Llama?

It replaces reasoning-model edges with Jev parallel Choice routing, described as sub-500ms and schema-safe because the answer must be one of your declared options.

Does deterministic routing mean it never picks the wrong agent?

No. The digest frames hallucinated routing options as the failure this avoids, but a wrong-but-valid choice is still possible if your option definitions overlap.

What setup is needed before the example handoff runs?

Create and activate a virtualenv, run pip install -e ., then run python examples/main.py to see test prompts distributed to mock agents.

Can I trust the speed claim for my own agent graph?

The digest only shows distribution to mock agents, so treat it as an integration pattern and measure latency and accuracy on your own intents before shipping.

How do I set up the langgraph-jev-router example?

Create a virtual environment, pip install -e . to install the package and its LangGraph dependency, then run python examples/main.py to see the router distribute test prompts to the correct mock agents by intent.

Which LangGraph concept does langgraph-jev-router replace?

A conditional edge: instead of a reasoning model choosing the branch, Jev's parallel Choice primitive routes intents, which the README frames as cutting latency and removing hallucinated routing options.

Does the langgraph-jev-router example need real agents?

No. The shipped example routes to mock agents so you can watch the intent distribution without wiring real backends; the README does not document setup beyond the virtual environment and pip install.

CommunityJev Agents & MCP

Langgraph Jev Router

LangGraph conditional edge that uses Jev parallel Choice routing between specialized agents instead of a generative model.

See highlights

Open github.com

Stars: 0
Language: Python
Published by: Community
Author: JTankariya
Last verified: Oct 2026

JTankariya/langgraph-jev-router

User repository on GitHub

View on GitHub

A native LangGraph conditional edge that replaces slow generative LLMs with TypeSafe AI's deterministic System One model (`Jev`). It enables ultra-fast (sub-500ms), schema-safe routing between specialized agents.

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

A native LangGraph conditional edge that replaces slow generative LLMs with TypeSafe AI's deterministic System One model (Jev). It enables ultra-fast (sub-500ms), schema-safe routing between specialized agents. Standard LangGraph implementations use reasoning models (like Claude or Llama) for conditional edges. This introduces significant latency and the risk of hallucinated routing options. This package uses Jev's parallel Choice primitive to route intents deterministically.

Quoted from the project's README. Read the full README.

Tagscommunity github

Works forJev for Routing Jev for Tool calling

Used inJev for Software & DevTools

Languages: Python

Highlights

Provides a native LangGraph conditional edge built on Jev parallel Choice.
Avoids generative latency and hallucinated routes by constraining answers to declared intents.
Installs with pip install -e . inside an activated virtualenv.
Includes examples/main.py distributing test prompts to mock agents by intent.

Watch out

Minimal example package, not a measured routing benchmark; accuracy claim rests on the included mock-agent demo. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

agent-harness-with-jev-llm

Demo of the LangChain Jev harness pattern in LangGraph: a fast classifier routes events and gates a risky tool call, leaving open-ended reasoning to a chat LLM. Entry is POST /events; output lands in JSONL files.

Jev Agents & MCP#community#github

Community

dhirajpatra/agent-harness-with-jev-llmPython

jeveloper

Claude Code plugin that puts Jev judgments in the agent loop to route tool calls, verify outputs, judge completion, and pick next actions with metered calls.

Jev Agents & MCP#community#github

Community

pur4v/jeveloperPython

vexjoy-agent

441

A four-layer agent toolkit for Claude Code, Codex, Factory, and Reasonix: 43 agents, 62 skills, 78 hooks, 147 scripts, and a Jev-backed router that gates dispatch on intent alignment.

Jev Agents & MCP#community#jevbest

Community

notque/vexjoy-agentPython

muse-jev-playbook

Agent-oriented playbook for using Jev as a cheap, fast decision layer that triages, classifies, scores, and gates work before expensive browser, research, retry, or subagent steps.

Jev Agents & MCP#community#awesomejev#catalog-import

Community

Bodila51/muse-jev-playbookPython

Tiermem

Tiered agent memory keeping compact summaries with source links over searchable raw history, where a router decides per query whether notes suffice or raw pages must be recovered.

Jev Agents & MCP#community#jevbest#catalog-import

Community

FreedomIntelligence/TiermemPython

liteagents

Python SDK that runs the same prompt, tools, and MCP setup across DeepAgents, Pydantic AI, Claude Agent SDK, Codex, and OpenCode by switching harness.

Jev Agents & MCP#community#jevbest#catalog-import

Community

BerriAI/liteagentsPython

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai