Maturana — Secure, Codex-native AI agent platform<br>maturana maturana.sh<br>DocsGitHubDiscord<br>open source · BSD-3-Clause

01Why Maturana<br>What makes it different.<br>Most agent frameworks are a wrapper around a model. Maturana is built around two ideas: the AI itself is the workflow, and an agent should be as isolated and auditable as any other production workload.<br>Secure by designHardware isolation, not containers<br>Agents are isolated with real hardware virtualization for maximum security — a Firecracker or Hyper-V microVM per agent, not just a container.

Zero trustSecrets your agent can't reach<br>Pipelock keeps secrets like API keys and credit-card numbers out of agent reach, and an egress proxy controls which systems your agents talk to. Treat your agent as an adversary and lock it down.

Build anythingEverything is a skill<br>Maturana is built on and for Codex, the premier OpenAI agent-engineering environment. Everything is a skill, from agent creation to tools — so you customise your agents with prompts and nothing else.

Self-evolvingAgents build their own tools<br>An internal WASM engine lets Maturana agents build their own tools on the fly — safely sandboxed, with no ambient authority.

Shared knowledgeA knowledge graph, beyond markdown<br>Maturana ships with a shared knowledge graph that scales past markdown files. Agents build their own memory, so you don't have to.

Lean & fastSmall Rust core, skills on top<br>Maturana is built in Rust with a modular core from the start. Skills are extensions to the core — you run only what you need.

02What it is<br>Secure, lean Codex-native agent orchestration for hardware-isolated AI agents you control.<br>Maturana is an open-source, Codex-native platform for building and running your own AI agents. You define an agent once, launch it into its own isolated virtual machine, and operate it entirely through Codex — the same tool you use to build it. Build and deploy your own skills in seconds.<br>▹Personal agents, not a chatbot. Each agent has its own identity, soul, runtime, channels, and permissions, declared in a single MATURANA.md contract.<br>▹Codex is the control plane. You create, edit, validate, and launch agents from Codex in the repo, using Maturana's bundled skills. No bespoke console to learn.<br>▹Each agent is isolated by hardware isolation, not Docker containers. Agents execute inside Hyper-V (Windows) or Firecracker (Linux) microVMs. The isolation boundary is hardware virtualisation, not a container.<br>▹Reach it where you already are. Pair an agent to Telegram, Slack, or Discord and talk to it like a person — with an interactive command menu and live model switching.

03Install<br>Get running in two commands.<br>The installer downloads the prebuilt binary, registers services, and installs the Codex skills. Then you build your first agent from Codex.<br>Prerequisites<br>Any hostAn authenticated harness<br>Agents need at least one AI harness signed in: the Codex CLI (codex login) or Claude Code. The installer checks this and tells you what's missing.

LinuxKVM for Firecracker<br>Linux hosts use Firecracker microVMs, which need KVM available. Pass --firecracker to provision the microVM host and boot-time fleet recovery.

WindowsHyper-V enabled<br>Windows hosts use Hyper-V as the isolation provider. Setup registers a privileged hostd task and boot services via one UAC-approved step.

Steps<br>LinuxFirecracker + KVM<br>$ curl -fsSL https://www.maturana.sh/install.sh | bashcopy<br>Installs the CLI, services, and Codex skills. Add -s -- --firecracker to also provision the microVM agent host.

WindowsHyper-V native<br>$ irm https://www.maturana.sh/install.ps1 | iexcopy<br>Installs the Windows runtime path with Hyper-V isolation, hostd, and boot services.

OperateCodex-first<br>$ cd ~/maturana && codexcopy<br>Open Codex in the repo and ask it to create and launch an agent, or invoke /skills directly. That's the whole workflow.

04Help<br>Get help.<br>Stuck on setup, or want to compare notes on agent design? The community is the best place to start.<br>DocsRead the documentation<br>The full README and docs/: install and your first agent, the MATURANA.md spec reference, architecture, and the Firecracker/Hyper-V operations guides.<br>Open the documentation

DiscordJoin the Discord<br>The fastest way to get unstuck. Ask setup questions, share agent patterns, and follow development with the community.<br>Join the Discord

GitHubRead the source<br>Maturana is open source under BSD-3-Clause. Read the code, file issues, and see exactly how isolation, pipelock, and the graph work.<br>Open the repo

05About<br>About me.<br>Anders Jensen-WaudAI operator & builderSydney · Copenhagen<br>16 years in strategy, tech, and transformation. MBB background. I architect and ship agentic AI systems for tier-1 financial services, telco, and PE — from boardroom strategy to agents in production.<br>jensenwaud.comLinkedInGitHubXEmail