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
dzhng/claude-agent-server
This project makes the Claude Agent SDK reachable over a network socket so that an application can run agent sessions inside an isolated cloud sandbox instead of the local process. The repository contains two packages. The server accepts WebSocket connections, forwards user messages into the Claude Agent SDK query loop and streams SDK messages back, with message handling and configuration kept in separate modules so the behaviour can be customised. A build script turns that server into an E2B sandbox template based on a Bun image: the build installs git, clones the repository, installs dependencies and configures the server to start automatically on port 3000, after which the named template is available for launching sandboxes. The client library, published to npm, is the intended entry point for application code. Constructing a client with an Anthropic API key and an E2B API key creates and manages the sandbox, opens the WebSocket connection, serialises messages, and releases resources when the session is stopped; passing a connection URL instead points the same client at a locally running or self-hosted server. Client options cover the sandbox template name and timeout, debug logging, and query configuration passed through to the server such as agent definitions, allowed tools and the system prompt, including the Claude Code preset with an appended section. A callback receives every message the agent emits, which lets the host application render streaming output or react to tool activity. The suggested workflow is to build the template, use the client library from a project, edit the server only when custom behaviour is needed, and test changes against a local server with the bundled example client before rebuilding the image. It is written in TypeScript for the Bun runtime and suits developers embedding Claude Code style agents in their own products.
https://github.com/dzhng/claude-agent-server
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.