> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lingxilearn.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# LingxiGraph documentation

> Build resumable, observable, production-scale multi-agent applications

LingxiGraph is a provider-neutral durable graph runtime. It represents agent workflows as typed state graphs and adds checkpoints, streaming events, human approval, version pinning, and a multi-tenant Agent Server.

<CardGroup cols={2}>
  <Card title="Install and choose a runtime" icon="download" href="./quickstart/installation">
    Choose the dependency-free embedded core, local development server, or complete production stack.
  </Card>

  <Card title="Build your first graph" icon="diagram-project" href="./quickstart/first-graph">
    Create an executable state graph from TypedDict schemas, nodes, and edges.
  </Card>

  <Card title="Start Agent Server" icon="server" href="./quickstart/agent-server">
    Run graphs through Studio, REST, SSE, and the Python SDK.
  </Card>

  <Card title="Browse the API" icon="brackets-curly" href="./api/overview">
    Explore resource models, authentication, errors, and every endpoint.
  </Card>
</CardGroup>

## What you can build

* Long-running agent workflows with checkpoints and human approval.
* Supervisor, handoff, swarm, group-chat, and parallel-review systems.
* Reliable task execution with stable idempotency keys, budgets, retries, and dead letters.
* Hybrid agent networks connected through Coze, OpenAI-compatible APIs, A2A, or MCP.
* Enterprise platforms that require OIDC, RBAC, tenant isolation, RLS, and OpenTelemetry.

## Two product layers

| Layer          | Primary objects                                              | Use it for                                                                   |
| -------------- | ------------------------------------------------------------ | ---------------------------------------------------------------------------- |
| Python runtime | `StateGraph`, `CompiledGraph`, `Runtime`, checkpoints, Store | Embedding in a service, single-process execution, unit tests                 |
| Agent platform | Graph, Assistant, Thread, Run, Schedule, REST/SSE, Worker    | Multi-tenant control planes, queues, independent scaling, unified operations |

<Tip>
  For a first evaluation, follow Installation → Build your first graph → Agent Server. It takes about ten minutes.
</Tip>

## Version and compatibility

This documentation targets LingxiGraph `2.0.0` on Python 3.11–3.13. Public server endpoints live under `/v1`. Each run pins a graph ID and version, so a deployment cannot change queued or paused work.

Continue with [Architecture](./concepts/architecture) and [Durable execution](./concepts/durable-execution) when you need the underlying guarantees.