Containers

Reproducible OCI container images, built with Nix, that sandbox AI coding agents such as Claude Code, Codex CLI and OpenCode so that a compromised or overreaching agent has limited access to the host filesystem and credentials.

• Containers

A reproducible vLLM Docker image built specifically for the NVIDIA DGX Spark's GB10 chip, with every component in the stack pinned by commit or digest so the same version file always rebuilds the same image.

• Inference
• Containers

A pinned Docker Compose build that serves a 27-billion-parameter Qwen model, quantized to 4-bit AWQ, on AMD's Strix Halo integrated GPU through vLLM with speculative decoding and tool calling.

• Inference
• Containers

A Docker Compose setup that runs the pi coding agent in an isolated container with file-system isolation, dropped privileges and persistent storage, including an offline mode using a local llama.cpp model.

• Coding agents
• Containers

A plug-and-play Docker image that runs vLLM with DFlash block-diffusion speculative decoding on NVIDIA Blackwell hardware such as the DGX Spark, optionally combined with TurboQuant KV-cache compression, to speed up decoding on Blackwell-exclusive NVFP4 tensor cores.

• Inference
• Containers

A self-hosted control plane for operating fleets of OpenClaw and Hermes AI agents on infrastructure the operator controls, deploying to Docker or Kubernetes with lifecycle management, live logs and a terminal, budgets and scheduled runs, and encrypted secrets.

• Containers
• Hosting

A unified vLLM serving configuration, distributed as a Docker Compose stack, for running large language models on NVIDIA DGX Spark GB10 hardware, supporting either a single-node setup or two nodes joined over a 200 Gbps RDMA link.

• Inference
• Containers

A Kubernetes-native checkpoint and restore system for NVIDIA GPU workloads. It saves a fully initialized pod's process and GPU memory, then restores that state on another node so new replicas skip cold start.

• Inference
• Containers

A 70 megabyte Docker image that runs Ollama on CPU only, built to be far smaller and faster to deploy than the official four-gigabyte Ollama image on systems without a GPU.

• Inference
• Containers

Fast-booting MicroVM sandboxes for AI agents, with warm pools for near-instant claims, a per-node control plane, and Go and Python SDKs for executing commands and files inside the guest.

• Containers

A containerized AI coding workstation that bundles OpenCode with more than fifty developer tools, a sandboxed headless browser and support for over ten AI providers, including a user's own Claude subscription.

• Coding agents
• Containers

A self-hosted private AI infrastructure and process-automation platform for Kubernetes, combining local model serving, a chat interface and workflow automation on the operator's own hardware.

• Containers
• Hosting

An autonomous agent harness for Kubernetes and GKE that continuously audits a fleet for compliance and security drift, opens pull requests with fixes through GitOps, and answers operational questions over chat.

• Security
• Containers

A containerized terminal development environment bundling modern CLI and TUI tools, several AI coding assistants, language SDKs and shell aliases, runnable the same way on a desktop, VPS or cloud workspace.

• Terminals
• Containers

A unified, sandboxable execution environment that runs Python code, shell commands and programmatic MCP tool calls together in a stateful IPython kernel.

• Containers

A starter kit that deploys production-ready generative-AI infrastructure on Amazon EKS with a single CLI command, including LLM serving engines, an AI gateway, vector databases and observability.

• Containers
• Hosting

A Helm chart that deploys a complete LLM operations stack on Kubernetes in one command, covering model serving, a unified API gateway, observability, autoscaling and fine-tuning.

• Inference
• Containers
• Monitoring

A Docker image that runs a self-hosted Whisper speech-to-text server with an OpenAI-compatible transcription and translation API, optional speaker diarization, and GPU acceleration.

• Speech
• Containers

A zero-trust sandbox framework that limits which files and commit history an AI coding model can see per session, logging every prompt, response, and data transfer.

• Security
• Containers

A source-available, self-hosted runtime for running fleets of autonomous AI agents in isolated containers, with a central credential vault and per-agent spending budgets.

• Agent frameworks
• Containers

A kernel-enforced sandbox for AI coding agents that wraps tools such as GitHub Copilot CLI, Claude Code or Gemini CLI so the agent can write code but is blocked from reading SSH keys, pushing to the default branch or exfiltrating secrets.

• Security
• Containers

A KEDA external scaler that reads GPU utilization and memory directly from NVIDIA's NVML library through a DaemonSet, so Kubernetes can autoscale GPU inference workloads without Prometheus or DCGM.

• Containers
• Monitoring

A Model Context Protocol server that lets an LLM client query and manage a Kubernetes cluster, including custom resources and Helm releases.

• MCP servers
• Containers

An MCP server that gives an AI agent a full graphical desktop it can see and control, moving the mouse, typing, launching apps and running shell commands, in a sandboxed virtual desktop or on the machine in front of you.

• MCP servers
• Containers