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
boxlite-ai/boxlite
BoxLite is a compute substrate for AI agents. Its unit is a Box, a hardware-isolated micro-VM that runs any OCI image and persists between uses, so an agent can install packages, write files and resume across turns without starting from cold. Isolation comes from a separate kernel per box, backed by KVM on Linux or Hypervisor.framework on macOS and combined with an OS sandbox layer, CPU and memory limits, an egress allow-list and secret injection in which real credential values never enter the VM. The engine is daemonless: it embeds as a library with no root and no background service, with an optional server mode. Four usage paths are documented. As a library it installs from PyPI, npm, crates.io or Go modules, and a C SDK is also provided; the Python example opens a box on a slim Python image, executes a command asynchronously and reads its stdout. As a binary it installs through a shell script or cargo into a user-local path with the runtime embedded, then runs any image directly from the terminal. As a service, a serve command exposes a REST API on port 8100 that accepts box creation over HTTP, and every CLI command can target a running server through a url flag. For larger deployments the repository includes infrastructure code that deploys the control plane into an AWS account for multi-tenant autoscaling boxes, requiring a Cloudflare-managed domain and Docker. Feature coverage listed in the README includes streamed execution with exit codes, an interactive PTY with live resize, per-command timeout, working directory, environment and run-as-user settings, entrypoint overrides, persistence across stop and restart, read-only and read-write volume mounts, per-box copy-on-write QCOW2 disks, bidirectional file copy, cloning and archive export or import, detached boxes that outlive the parent process, outbound networking with local port forwarding and tunnels, private registry support and per-box metrics. Apache-2.0 licensed.
https://github.com/boxlite-ai/boxlite
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.
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.