Skip to content

matic.shThe AI operating system 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.

What is matic?

matic is an operating system for running structured teams of AI agents. You define a goal, connect tools and data, and operate agents that work together to achieve real business outcomes.

Instead of acting like a chatbot or a single-purpose workflow, matic takes inspiration from how human organisations work — structuring autonomous work around goals, teams, tasks, routines, memory, policies, and communication.

matic doesn't call AI models directly. It sits above agent runtimes like Claude Code, Codex CLI, and Gemini CLI, coordinating them through a normalised adapter layer. No lock-in at any level of the stack.

How it works

matic turns inbound signals into coordinated work, executes against defined outcomes, and compounds what it learns over time.

IngestChannel messageWebhook eventRoutine emissionSignal


RouteSignalClassify & interpretRoute to agent or groupActivation


PlanActivationDecompose into tasksStaff agents via probesWork Items


ExecuteWork ItemsAssemble context envelopeAgent runtime executesRun


DeliverRunValidate against contractHITL checkpointArtifact


LearnArtifactObserve outcomeHypothesize improvementsEvolve probes & memory

The learning loop is not aspirational — it's a mandatory phase. After every engagement, agents enter a learning state where experience is consolidated, probes are refined, and institutional knowledge is captured as reusable archetypes.

Architecture

Filesystem-first. All operational state — agents, projects, tasks, memory, policies — is stored as markdown and YAML files. No database required.

Git-native. Git is the persistence and collaboration layer. Every state change is a commit. Work is inspectable, versioned, diffable, and recoverable.

Agent-runtime agnostic. matic coordinates agent runtimes through adapters that normalise their interfaces. Swap runtimes without changing your org.

Channel-driven. Humans interact through channels — Slack, Telegram, WhatsApp, Discord, email, or the built-in terminal. Shell access is optional, not required.

Human control is first-class. Policies, guardrails, HITL checkpoints, and decision records ensure humans stay in the loop where it matters. Full audit trail by default.

Core primitives

PrimitivePurpose
OrgThe root operational context — a git repository containing everything
CharterThe org's governing objectives, constraints, and scope
AgentA persistent autonomous actor with identity, memory, and evolving competence
ProjectA bounded, goal-directed body of work
TeamA composition of agents assembled to execute a project
SignalAn inbound event from channels, webhooks, routines, or schedules
Work ItemA bounded deliverable with acceptance criteria and a floor/ceiling contract
RunAn execution record capturing what an agent did, when, and what it produced
PolicyA declarative rule defining what is permitted, with enforcement levels

What you can build with matic

matic is designed for running entire business operations autonomously — not just answering questions or generating content:

  • Lead generation operations — agents that prospect, qualify, and nurture
  • Content engines — teams that research, write, edit, and publish
  • Research desks — agents that monitor, analyse, and synthesise
  • Competitor monitors — continuous intelligence from public sources
  • Development teams — agents that plan, implement, test, and ship code

Documentation

SectionWhat you'll find
Getting StartedInstallation, first org, first agent, first run
Core ConceptsThe mental model — scopes, primitives, work lifecycle
AgentsIdentity, archetypes, probes, lifecycle, collaboration
WorkflowSignals, activation, work items, runs, delivery
GovernancePolicies, HITL, decisions, audit, budgets
PlatformCLI, daemon, channels, runtimes, MCP, plugins
ReferenceSchemas, configuration, filesystem layout, appendix