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
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.
nndeploy/nndeploy
nndeploy is a workflow-based multi-platform AI deployment tool that enables efficient, high-performance, and customizable deployment of AI models across cloud, desktop, mobile, and edge platforms using a visual drag-and-drop interface and extensive framework support.
xingyaoww/code-act
CodeAct is a framework that improves large language model agents by using executable code as a unified action space, enabling dynamic multi-turn interactions and outperforming traditional text and JSON action representations.
nasa-jpl/rosa
ROSA is an AI-powered assistant that enables natural language interaction with ROS1 and ROS2 robotics systems to help developers inspect, diagnose, and operate robots efficiently.
MeetKai/functionary
Functionary is a chat language model that dynamically interprets and executes functions or plugins, enabling advanced tool usage and result interpretation for interactive AI applications.
e2b-dev/awesome-ai-sdks
A curated database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging, and deploying autonomous AI agents, maintained by the e2b team building an operating system for AI agents.
aliyun/wuying-agentbay-sdk
Alibaba Cloud SDK for on-demand cloud sandboxes for AI agents, giving browser, desktop, mobile and code-execution sessions through Python, TypeScript, Go and Java clients.
cloudflare/sandbox-sdk
TypeScript SDK for running untrusted code in isolated Cloudflare containers from Workers, with command execution, file operations, background processes and public preview tunnels.
microsoft/Agents
The Microsoft 365 Agents SDK enables developers to build and deploy intelligent, multichannel agents across Microsoft 365, Teams, Copilot Studio, and Webchat using AI services of their choice.
docker/compose-for-agents
Docker collection of self-contained Compose projects that run agent stacks locally, wiring agent frameworks, MCP tool servers and local or hosted models together with a single docker compose up.
ArcadeAI/arcade-ai
ArcadeAI/arcade-ai is a developer platform with a Python SDK and CLI that enables building, deploying, and managing tools for AI agents to interact with the world efficiently.
kossakovsky/n8n-install
Selfhost AI is a Docker Compose installer that deploys more than thirty self-hosted AI and automation services, including n8n, Flowise, Dify, Ollama and vector databases, behind Caddy with automatic HTTPS.
agentscope-ai/agentscope-runtime
Python runtime for putting agents into production, providing sandboxed tool execution, Agent-as-a-Service streaming APIs, observability and local, Kubernetes or serverless deployment; now folded into AgentScope 2.0.
Katakate/k7
Katakate k7 is self-hosted infrastructure for lightweight VM sandboxes, letting AI agents execute untrusted code at scale on Kata, Firecracker, QEMU and Kubernetes.
awslabs/fullstack-solution-template-for-agentcore
AWS Labs starter template that deploys a React frontend, Cognito authentication and an Amazon Bedrock AgentCore backend through CDK or Terraform, giving teams a working full-stack agent application to fork.
dzhng/claude-agent-server
claude-agent-server wraps the Claude Agent SDK in a WebSocket server that is deployed as an E2B sandbox template, with a TypeScript client library that creates the sandbox, streams messages bidirectionally and cleans up the resources.
miantiao-me/cloud-code
Containerized deployment of the OpenCode agent on Cloudflare Workers and Containers, with Basic Auth, S3 or R2 persistence through TigrisFS, SSE streaming and a bundled cloudflared tunnel.
WorkflowAI/WorkflowAI
WorkflowAI is an open-source platform that enables teams to rapidly build, test, and deploy AI features with support for multiple AI models, flexible deployment options, and advanced observability and cost tracking.
Th0rgal/sandboxed.sh
sandboxed.sh is a self-hosted mission-execution backend that runs Claude Code, OpenCode, Codex, Gemini and Grok agents inside isolated Linux workspaces, driven over MCP by a separate coordinator that dispatches and tracks the work.
undera/perfmon-agent
PerfMon Server Agent is a Java-based tool for remotely accessing and monitoring a wide range of system performance metrics on servers using a simple plain-text protocol.
MLT-OSS/open-assistant-api
Open Assistant API is an open-source, self-hosted AI assistant API framework that supports multi-model LLM integration, RAG engines, custom functions, and tool extensions with seamless OpenAI compatibility.
palico-ai/palico-ai
Palico AI is an integrated framework that enables developers to build, improve, and productionize Large Language Model applications with flexibility, advanced features, and extensive integrations.
jenkinsci/docker-agent
Jenkinsci/docker-agent provides Docker images for Jenkins agents, including base and inbound agents, facilitating containerized Jenkins automation with support for multiple platforms and JDK versions.
C0deMunk33/bespoke_automata
Bespoke Automata is a platform for creating, testing, and deploying complex AI agents locally with a graphical interface and API endpoints.