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
agentscope-ai/agentscope-runtime
AgentScope Runtime is the production runtime layer of the AgentScope project. It addresses the part of agent engineering that comes after the agent logic is written: running tool calls safely, exposing the agent over a network API, and observing what it does. Tool sandboxing executes every tool invocation inside a hardened, isolated environment, so that shell commands, browser sessions, filesystem access and arbitrary code produced by the model cannot reach the host. The Agent-as-a-Service layer wraps an agent as a streaming HTTP service with a stable request and response contract, session and state handling, so that a front end or another service can consume it without knowing the underlying framework. Deployment targets include a local process, Kubernetes and serverless platforms, which lets the same agent scale elastically without code changes. Full stack observability collects logs and traces across model calls, tool calls and sandbox activity, and a web UI is provided for inspecting runs interactively. The runtime is deliberately framework agnostic: besides AgentScope itself it can host agents written with other mainstream agent frameworks, and it speaks the Agent-to-Agent protocol and the Model Context Protocol so that external tools and peer agents can be attached. The package targets Python 3.10 and above, is published on PyPI as agentscope-runtime, carries an Apache 2.0 licence and ships a bilingual cookbook plus a samples repository. The maintainers have announced that all of these capabilities have been natively integrated into AgentScope 2.0 and that this repository is moving to read-only mode, so new users are directed to the main AgentScope project while this code remains as a reference implementation of a sandboxed agent runtime.
https://github.com/agentscope-ai/agentscope-runtime
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.