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
Katakate/k7
Katakate, distributed as the k7 CLI, provides self-hosted infrastructure for creating, managing and orchestrating lightweight virtual-machine sandboxes that safely execute untrusted code. Its primary motivation is AI agents that need to run arbitrary generated code at scale, though the same infrastructure also serves custom serverless workloads, hardened CI/CD runners without Docker-in-Docker risk, and blockchain execution layers. The stack builds on K3s Kubernetes for orchestration, Kata Containers to wrap containers in lightweight VMs, Firecracker for fast boots and a minimal attack surface, QEMU where a fuller virtual machine monitor is wanted, Longhorn for replicated persistent root disks, a devmapper thin-pool snapshotter for efficient disk use across many VMs on one node, and Cilium CNI with FQDN-based egress policies. Three sandbox backends can be provisioned per node and selected per sandbox. The Firecracker plus devmapper backend favours fast ephemeral sandboxes. The QEMU plus Longhorn backend adds replicated persistent disks with named snapshots, restore, disk-only fork and cross-node mobility. The third backend, k7d, is the project own KVM-based microVM runtime using erofs images, reflinked XFS and guest tmpfs, and it reaches roughly two seconds from create to ready, copy-on-write forks of a running VM disk and memory in about five milliseconds, and sub-second pause and resume with memory preserved in place. Published performance figures are medians measured on a single Hetzner node and documented with methodology. Additional features include Docker build and run inside sandboxes through a sidecar, multi-node clusters provisioned with Ansible and Longhorn, and a full snapshot, pause, resume, fork and restore lifecycle. Interfaces are a CLI, an HTTP API and a Python SDK installed as k7-sdk. The project is in beta and under security review. Licensed Apache-2.0.
https://github.com/Katakate/k7
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.