ollama/ollama
Ollama is a versatile platform that enables easy deployment, customization, and management of large language models locally across multiple operating systems with support for various model formats and a REST API.
Awesome AI Agents › AI Agent Deployment
awslabs/fullstack-solution-template-for-agentcore
The Fullstack Solution Template for AgentCore, called FAST inside the repository, is an AWS Labs starter project for building web applications on top of Amazon Bedrock AgentCore. Forking and running a few CDK commands deploys a complete stack: a React frontend written in TypeScript with Vite, Tailwind CSS and shadcn components hosted on AWS Amplify, an agent running inside AgentCore Runtime, an AgentCore Gateway fronting Lambda-based tools, and API Gateway endpoints. Terraform manifests are provided as an alternative to CDK. Authentication is wired end to end with Amazon Cognito: the browser obtains a user pool JWT, the runtime validates it, and the runtime then reaches the gateway over an OAuth2 client credentials grant whose token carries the propagated user identity, letting Cedar policies enforce fine-grained access at the gateway. The baseline application is deliberately minimal, a multi-turn chat agent with two example capabilities, a Lambda text analysis tool behind the gateway and a direct integration with the Bedrock AgentCore Code Interpreter for sandboxed Python execution with session state. The template is agnostic about the agent SDK, so Strands, LangGraph or another library can sit inside the runtime, and it is agnostic about the coding assistant used to extend it. A stated design choice is that security and architecture practices are recorded as documentation and steering files in the repository rather than being hard-coded, so an AI coding assistant reading that context can customise the frontend and infrastructure while following the intended patterns. It is aimed at solution engineers and delivery teams who need a security-reviewed AgentCore deployment quickly and would rather not write frontend or infrastructure code themselves.
https://github.com/awslabs/fullstack-solution-template-for-agentcore
Also in AI Agent Deployment
alibaba/nacos
Nacos is a dynamic service discovery, configuration, and service management platform designed to simplify building and managing cloud-native applications and microservices.
e2b-dev/E2B
E2B is an open-source secure cloud runtime infrastructure that enables safe execution of AI-generated code in isolated sandboxes for AI applications and agents.
GoogleCloudPlatform/agent-starter-pack
A collection of production-ready Generative AI Agent templates for Google Cloud that accelerates development by addressing deployment, evaluation, customization, and observability challenges.
zebbern/claude-code-guide
Claude Code Guide is a comprehensive and authoritative resource providing detailed instructions, tips, and references for using the Claude Code CLI tool to interact with the Claude AI model, including advanced features and MCP integration.
boxlite-ai/boxlite
Rust engine giving AI agents hardware-isolated persistent micro-VMs that run any OCI image, embeddable as a daemonless library in Python, Node, Go, Rust or C, or run as a CLI, REST server or cloud control plane.
jim-schwoebel/awesome_ai_agents
A comprehensive and community-driven repository offering over 1,500 curated resources, tools, and projects related to AI agents for various applications and development needs.
Forethought-Technologies/AutoChain
AutoChain is a lightweight and extensible framework that simplifies building and automatically evaluating custom generative agents powered by large language models using custom tools and simulated multi-turn conversations.