skills.rest
litestar-org
litestar-orgOFFICIAL
Explore all skills by this author →
Website𝕏@LitestarAPIGitHub

litestar-ai-serving

Build HTTP AI agent endpoints with Litestar and Google ADK.

13|Updated Apr 15, 2026
Search Tags:#dependency-injection#session-persistence#google-adk#vertex-ai#ai-serving#litestar
One-click install
npx skills add https://github.com/litestar-org/litestar-skills --skill litestar-ai-serving
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: litestar-ai-serving
Source: https://github.com/litestar-org/litestar-skills/tree/main/plugins/litestar/skills/litestar-ai-serving
Command: npx skills add https://github.com/litestar-org/litestar-skills --skill litestar-ai-serving

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the recurring challenge of building consistent, production-ready HTTP-facing AI agent endpoints with Litestar and Google ADK, eliminating guesswork around dependency injection, session persistence, error handling, and security guardrails for model workflows.

Core Features & Use Cases

  • Canonical ADK Integration Patterns: Pre-vetted wiring for Google ADK LlmAgent, Runner, and SQLSpecSessionService via Dishka dependency injection, with explicit guidance on scope and runtime introspection constraints.
  • Production Guardrails: Built-in patterns for handling missing Vertex AI credentials, request timeouts, unbounded model call blocking, and authorization enforcement for agent endpoints.
  • Reference Implementation Templates: Ready-to-use patterns for non-streaming chat handlers, persona-augmented system prompts, tool-use-first agent workflows, and multi-turn session memory backed by SQLSpec.
  • Use Case Example: If you are building a customer support chat endpoint that uses Vertex AI, maintains conversation history across HTTP requests, and enforces auth on agent tools, this Skill provides the exact patterns to implement it correctly the first time.

Quick Start

Use the litestar-ai-serving skill to build a production-ready HTTP chat endpoint that integrates Google ADK, maintains multi-turn session state, and enforces security guardrails for AI model workflows.

Frequently Asked Questions about litestar-ai-serving

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build production-ready HTTP endpoints for AI agents using Litestar and Google ADK?▼

To build production-ready HTTP endpoints for AI agents using Litestar and Google ADK, use pre-vetted wiring patterns for Runner and LlmAgent orchestration, applying typed DTOs at HTTP boundaries and dependency injection for component scope management.

How does session persistence work for multi-turn conversations in Litestar AI endpoints?▼

Session persistence for multi-turn conversations in Litestar AI endpoints works via SQLSpecSessionService, which maintains conversation history across HTTP requests and provides runtime introspection for stateful agent workflows.

Can I use Dishka dependency injection with Google ADK components in a Litestar application?▼

Yes, you can use Dishka dependency injection with Google ADK components in a Litestar application to wire LlmAgent and Runner instances, with explicit guidance on managing scope and runtime introspection constraints.

What's the best way to handle Vertex AI credential errors and timeouts in AI agent endpoints?▼

The best way to handle Vertex AI credential errors and timeouts in AI agent endpoints is to apply built-in production guardrails that catch missing credentials, manage request timeouts, and prevent unbounded model call blocking.

How do I enforce authorization and security guardrails on agent tool access in Litestar?▼

To enforce authorization and security guardrails on agent tool access in Litestar, apply the provided patterns for authorization enforcement specifically designed for agent endpoints serving LLM-powered features.

Does the litestar-ai-serving skill support streaming chat handlers?▼

The litestar-ai-serving skill provides ready-to-use reference templates for non-streaming chat handlers, tool-use-first agent workflows, and persona-augmented system prompts rather than streaming responses.

Related Skills

Explore More Software Engineering Skills→
phuetzphuetz
30

terraform-ansible

Provision cloud infrastructure with Terraform and configure it using Ansible playbooks.

Community
Advanced
TencentCloudBaseTencentCloudBase
1.1k

cloudbase-agent-ts

Build and deploy AG-UI compatible AI agents as HTTP services with CloudBase.

Official
Advanced
litestar-orglitestar-org
13

litestar

Route Litestar development tasks to the appropriate specialized skills.

Official
Intermediate
wollfoowollfoo

google-adk-python

Builds, evaluates, and deploys AI agents with Google ADK Python to Vertex AI or Cloud Run.

Community
Advanced