---
id: langgraph-runtime-inmem
version: "0.32.4"
license: Elastic-2.0
license_treatment: unclear
maintenance: active
---

# langgraph-runtime-inmem — Inmem implementation for the LangGraph API server.

License: unclear · Maintenance: active · Downloads: 3.0M/mo

## What it is and what it does

langgraph-runtime-inmem is the in-memory backend for LangGraph's runtime API, allowing you to execute graph-based workflows directly in process without requiring a separate persistence layer. It sits within the LangGraph ecosystem alongside dependencies like langgraph, langgraph-checkpoint, starlette, and structlog, providing a lightweight option for running stateful workflows.

The package is designed as a drop-in runtime implementation for the LangGraph API server contract. It handles graph execution, state management, and scheduling (via croniter for timed tasks) entirely in memory, making it suitable for scenarios where you want to prototype, test, or run workflows without external infrastructure. The in-memory design trades persistence and horizontal scaling for simplicity and low operational overhead.

Use it for:

- Prototyping and testing LangGraph workflows locally before deploying to a persistent runtime
- Running short-lived or development-stage AI agent workflows that don't require state recovery
- Building single-process applications that orchestrate LangGraph-based tasks with built-in scheduling
- Integrating LangGraph execution into existing Starlette-based web services for real-time agent interactions

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Provides an in-memory runtime implementation for the LangGraph API server, enabling graph-based workflow execution without external persistence.

Yes, if you are building with LangGraph and need a lightweight, low-friction runtime for development, testing, or single-process deployments. The active maintenance and low install friction are positive signals. However, clarify the Elastic-2.0 license terms for your use case first, and confirm that in-memory execution meets your durability and scaling requirements before using in production.

## Install

pip install langgraph-runtime-inmem
uv add langgraph-runtime-inmem
poetry add langgraph-runtime-inmem

## Installing langgraph-runtime-inmem

Before you install: Low install friction with a pure Python wheel. Active maintenance as of 1 day ago. Requires Python 3.11 or later.

License in practice: License treatment is unclear; Elastic-2.0 may carry restrictions or obligations not immediately apparent from standard SPDX classification. Review the license terms before adopting in production.

Quickstart:

pip install langgraph-runtime-inmem

from langgraph_runtime_inmem import InMemoryRuntime

runtime = InMemoryRuntime()

Requires Python 3.11 or later.

Verify before relying:

- Whether Elastic-2.0 license permits commercial or proprietary use without additional licensing
- Whether the in-memory runtime is suitable for production workloads or intended for development/testing only
- Performance characteristics and memory scaling limits for large or long-running graphs

## Package facts

- License: Elastic-2.0 (unclear)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 3.0M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

langgraph runtime implementation, in-memory graph execution, langgraph api server, workflow orchestration runtime, langgraph inmem backend, langgraph, workflow-orchestration, ai-agents

[View on SkillFed](https://skillfed.io/packages/langgraph-runtime-inmem) · [View on PyPI](https://pypi.org/project/langgraph-runtime-inmem/)