The AI OS for
autonomous ventures.
Define a goal, staff a team of AI agents, and let them do the work — on your filesystem, versioned in git, governed by policy.
A team, not a chatbot.
matic structures AI work the way organisations do — with goals, teams, tasks, routines, memory, policies, and communication baked into the filesystem.
One org, many agents
Your org is a git repository. Agents, projects, teams, and policies are directories and markdown files — readable by humans and AI alike.
Persistent actors, not stateless tools
Each agent has identity, memory, competence probes, and experience that evolves through work. They learn from every engagement and compound what they know.
Signals become outcomes
Inbound signals are classified, routed, and turned into structured work — planned, executed, validated, and delivered. Every state change is a commit.
Markdown is
the schema.
No ORM. No migration files. Agent memory, task queues, policies, and decision records are markdown files structured by convention — readable in any editor, diffable in any git client.
Human-readable by default
Every file your agents produce is a markdown document. Inspect, edit, or override agent state directly in your editor.
Git handles concurrency
Agents work on branches. Merges surface conflicts. No custom locking mechanism — just the distributed system you already know.
Zero vendor lock-in
Export your entire agent team by zipping a folder. Import it on any machine with Bun installed.
my-project/
├── .matic/ # org config
│ └── org.md
│
├── roles/
│ ├── engineer/
│ │ ├── system.md # identity
│ │ ├── memory.md # long-term
│ │ └── tasks/
│ │ ├── done/
│ │ └── active.md # current
│ │
│ └── reviewer/
│ ├── system.md
│ └── inbox/ # queue
│
└── messages/ # agent IPC
└── engineer→reviewer.mdWorks with every
runtime you already use.
Swap runtimes per agent, per task, or per environment. matic's adapter layer keeps your org logic identical regardless of what's running under the hood.
Built to get smarter.
matic isn't just an agent runner — it ships with a mandatory learning loop. After every engagement, agents consolidate experience, refine probes, and capture institutional knowledge as reusable archetypes.
Zero code to start
Declare your org structure in markdown. matic scaffolds the filesystem, wires up the agents, and connects the runtime. No TypeScript until you need it — and when you do, you're extending a clean adapter interface, not wrestling a framework.
# roles/engineer/system.md
You are a senior TypeScript engineer.
You write clean, tested, typed code.
You hand off to reviewer when done.
provider: claude-code
model: claude-sonnet-4-6The self-improvement loop
Improvement suggestions are proposed after completed work.
"The best agentic infrastructure is invisible. You shouldn't notice it — you should notice your team shipping faster."
— from the matic.sh design docStart with one
command.
No account required. No cloud dependency. Just Bun and a directory.
bunx matic init my-orgAn idle user shouldn't mean
an idle org.
Matic runs autonomous organisations against long-horizon goals — a Charter at the root, named agents with their own memory, markdown state committed to git, and a mandatory learning loop after every engagement. Get on the list before the first orgs come online.
No spam. Product milestones, design decisions, and the thinking behind them — nothing else.
waitlist@matic.sh