Blaxel

AX is Google's open agentic orchestration runtime for declaring and running autonomous agent workloads in Kubernetes clusters. It defines Tasks, Workspaces, Gateways, and Models as ax.io/v1alpha1 manifests: Tasks run agent code in isolated sandboxes, Workspaces preconfigure Git repositories, MCP servers, and skill packages, Gateways restrict outbound traffic with host allowlists, and Models configure the platform's LLM access through Kubernetes secrets. The control plane runs on Agent Substrate and is operated through a kubectl-shaped CLI that applies manifests, watches task status, opens SSH sessions into sandboxes, and suspends or resumes checkpointed agents. AX is described as being designed for high-throughput cluster operation and is still subject to breaking changes before a stable release. It is distributed under the Apache License 2.0.

LoopX is an open-source, provider-neutral state kernel and local-first control plane for long-horizon AI agents and peer agent teams. It runs on top of agent harnesses such as Codex, Claude Code, Cursor, dsh, or a custom harness rather than replacing them, keeping objectives, gates, tasks, evidence, quotas, schedules, recovery state, and handoffs durable across bounded turns, sessions, tools, and agents. Its control layer makes semantic decisions about what happens next and supports governance, recovery, human-agent collaboration, and reviewable work. The accompanying personal agent workspace stores goals, attention, conversations, tasks, files, schedules, and recovery state locally across restarts; its supported browser/PWA dashboard can continue work across registered agent sessions and use typed previews, explicit confirmation, and receipts for protected changes.

fx is an open-source coding-agent harness and command-line interface written in Zig by Vercel Labs. It is designed as a compact Unix-like alternative to a terminal IDE, with interactive and one-shot requests for inspecting and modifying repository code, running shell commands, and saving or resuming sessions. The agent supports skills, MCP tools, plugins, subagents, permission rules, and headless requests, and can be embedded natively or through WebAssembly. It is model-agnostic, supports local and cloud inference, is distributed under the Apache-2.0 license, and is marked experimental by its repository.

Microsandbox is a local-first microVM runtime and library for running untrusted workloads, including AI-agent tasks, user code, plugins, CI jobs, development environments, scrapers, and automation. It uses hardware-level isolation and runs standard OCI container images from registries such as Docker Hub and GHCR, with Docker-like image, command, shell, and volume workflows. The project provides SDKs for TypeScript, Rust, Python, Go, and Ruby, along with a CLI for booting and controlling sandboxes. Applications can create microVMs as child processes without a setup server or long-running daemon; sandboxes can also run detached for long-lived sessions. Agent Skills and an MCP server support agent-created sandboxes, and the project documents secret handling intended to keep keys out of the VM. It runs on Linux, macOS, and Windows, with platform-specific virtualization requirements, and is described as beta software.

LobeHub is a self-hostable platform for organizing teams of AI agents, presented as a chief agent operator. It treats agents as units of work and provides tools to create and configure agents, schedule and report on their operations, coordinate them in agent groups, and monitor shared workspaces and memory. The platform provides access to multiple models and modalities, an agent builder, a library of skills and MCP-compatible plugins, and an IM gateway for interacting with agents through existing chat services. It can be deployed using Docker or listed cloud deployment options, and is described as being under active development.