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
kossakovsky/n8n-install
Selfhost AI, distributed from the n8n-install repository, is an installation template that stands up a complete private AI and automation environment on a single Ubuntu host with one command. An interactive wizard asks which services to include, generates secrets automatically and writes the Docker Compose configuration, so no manual per-service setup is required. Caddy is always deployed as a reverse proxy and obtains Let's Encrypt certificates automatically, and Postgres and Redis are always included as the shared database and cache layer. The selectable catalogue is oriented toward LLM and agent work: n8n for workflow automation in queue mode, where the number of workers and task runners is chosen at install time so workflows can be processed in parallel; Flowise as a low-code builder for AI agents and chains; Dify as an application development platform covering workflow management, prompt engineering, retrieval pipelines and agent orchestration; Ollama for running language models locally; Open WebUI as a chat interface over those local models; Qdrant and Weaviate as vector databases for retrieval; Crawl4ai for AI-oriented web crawling; Docling for converting PDF, Office and HTML documents into Markdown or JSON with OCR support; Supabase as a backend; ComfyUI for node-based image generation pipelines; Appsmith for internal tool and dashboard building; and a Grafana plus Prometheus monitoring stack. The installer can also import several hundred community n8n workflows during setup. Operational concerns are covered by health checks, declared service dependencies, an upgrade path and a Makefile of shortcut commands. The project is licensed under Apache 2.0 and positions itself as a self-hosted alternative to commercial automation services. It targets homelab users and small teams who want agent and retrieval tooling running on infrastructure they control, rather than developers building an agent framework themselves.
https://github.com/kossakovsky/n8n-install
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.