Mirror Neuron Documents

MirrorNeuron Documentation

Documentation for MirrorNeuron Documentation.

MirrorNeuron Documentation

MirrorNeuron is a durable runtime and control plane for adaptive, message-driven AI workflows. It runs on a laptop, on edge boxes, or across a small cluster.

The documentation has two goals:

  • A new user should install, configure, run, and safely test MirrorNeuron in under 10 minutes.
  • A new contributor should understand the architecture well enough to make a small pull request in under one hour.

Start Here

  1. README: project overview, quick start, and doc map.
  2. Component Guide: choose the right folder and validation command.
  3. Quickstart: validate and run your first workflow.
  4. Installation: install runtime dependencies and start local services.
  5. Security Model: understand what powers you are giving the runtime.
  6. Troubleshooting: common setup, Redis, OpenShell, and cluster errors.

Documentation Map

PageTypeUse it when
Component GuideOverviewYou need the repository map, folder responsibilities, and local validation commands.
QuickstartTutorialYou want the shortest path to first success.
InstallationTutorialYou need to install Redis, OpenShell, Elixir, and Python tooling.
ExamplesTutorialYou want to choose the right checked-in blueprint.
Skill CatalogReferenceYou need centralized summaries for reusable skill packages.
Cluster GuideHow-toYou need to start or inspect a multi-box runtime.
Nomad-Inspired Runtime FeaturesOverviewYou want the status and code map for reconciliation, job types, policies, drain, services, resources, deployments, and schedules.
Redis High AvailabilityHow-toYou need Redis Sentinel failover.
Monitor GuideHow-toYou need to inspect live jobs and events.
CLI ReferenceReferenceYou need exact CLI commands and options.
Environment VariablesReferenceYou need config names, defaults, and effects.
API ReferenceReferenceYou need HTTP or Elixir API shapes.
Job Bundle FormatReferenceYou are writing or validating manifest.json.
Python SDKReferenceYou want to compile Python workflow definitions into bundles.
Blueprint StandardReferenceYou need the cross-blueprint contract for manifests, run stores, agents, aliases, artifacts, privacy, and UI surfaces.
Services and Health ChecksHow-toYou need service declarations, registry lookup, or required service preflight.
Model RuntimeHow-toYou need to install, inspect, validate, or use local Docker Model Runner LLMs.
Docker and OpenShell for BlueprintsHow-toYou need local files, ports, web UIs, host services, or sandbox resources to work first time.
Resources and DevicesReferenceYou need CUDA, Metal, GPU memory, ports, volumes, or runtime-driver placement.
DeploymentsHow-toYou need rolling, canary, promotion, rollback, or versioned long-running jobs.
Schedules and EventsHow-toYou need cron, delayed, or event-triggered jobs.
Runtime ArchitectureExplanationYou want the control-plane/execution-plane mental model.
Cluster ArchitectureExplanationYou want leader, node, and relocation behavior.
Reliability GuideExplanationYou want recovery, leases, backpressure, and retention behavior.
Security ModelExplanationYou need trust boundaries and safe defaults.
Blueprints and SkillsHow-toYou are extending MirrorNeuron safely.
TestingReferenceYou need the test matrix and commands.
ContributingTutorialYou are preparing a pull request.
Documentation StyleReferenceYou are editing docs.

First Safe Workflow

After Redis and the runtime are started, run the smallest checked-in workflow:

mn blueprint run message_routing_trace

Expected output:

Job submitted successfully

Security Quick Read

MirrorNeuron can run local commands, create sandboxes, call APIs, pass selected secrets into workers, and coordinate jobs across boxes. Before using it in a shared or production environment:

  • Review every bundle before running it.
  • Keep pass_env narrow.
  • Prefer OpenShell over HostLocal for less-trusted worker code.
  • Keep Redis protected and use Redis Sentinel for multi-box reliability.
  • Change MN_COOKIE for any non-local cluster.
  • Bind API/gRPC listeners only to trusted networks.

Read Security Model for the full checklist.

Contributor Path

  1. Read Runtime Architecture.
  2. Run Testing commands.
  3. Make a small focused change.
  4. Update docs when behavior changes.
  5. Use the Contributing checklist before opening a PR.

On this page