OpenRig

In OpenRig, each agent has a clear role and address, can communicate directly with one another, and can run across multiple machines.

In OpenRig, knowledge about "how messages are integrated" is stored only once and has a fixed address that stays the same when it changes; agents can use rigsend to discover and contact other agents that are online.

The author cautions that the map is not the territory: the ontology is files on disk, Markdown headings, links and commands, and one still needs to actually open the files to confirm system behavior.

The author placed the "doghouse moon base" story in the lore folder as experience passed between agents, retold at both initialization and after context compaction.

In OpenRig, knowledge is addressable via file paths and Markdown headers, and custom views can be composed through references.

The author believes giving agents good examples is more effective than giving them a pile of facts and rules.

The core problem the author encountered was agents repeatedly reinventing the wheel, building a new set in parallel alongside an existing implementation.

RigSend is a point-to-point communication method that inputs messages directly into a specific Agent's terminal, offering two modes: waiting for the target to be idle and checking the screen after sending to confirm receipt.

The key to choosing a communication method in OpenRig depends on two questions: who needs to hear this message, and whether it needs to leave a persistent record.

In OpenRig, Delivered only means the message has been input, not that it has been read.

queue is the team's official memo board introduced in OpenRig from Episode 6, serving as an accountability anchor where each item requires a specific seat to explicitly claim or reject it.

RigBroadcast is used to notify multiple Agents at once; forgetting to specify a particular rig will spread the message to all sessions on every rig including the kernel, and using --pod alone will match the dev pod on every rig.

Each rig has a Chat Room persistently maintained by a daemon, which serves awareness purposes and cannot replace the queue.

OpenRig's transcript rolls and saves copies of each screen like a dashcam, but only retains recent history and discards the earliest portions, and is not a complete recording.

rig ask does not call another AI; it only runs a plain-text search on the saved transcript text, but offers the option to wake a saved session for direct questioning, which runs a real Agent and consumes tokens.

The daemon in the OpenRig architecture serves as the infrastructure layer, persisting chat room records, maintaining inbox/outbox status, logging seat event streams, and providing real-time data for the dashboard and views.

The RIG commands used by Agents in OpenRig are exactly the same as those used by human operators, and both run them directly in their respective terminals.

OpenRig's communication philosophy can be distilled as: use send to ask, use queue to record accountability, use capture to observe, and use transcript to search.

openrig is an open-source project for building your own agent network from Claude Code, Codex, and Pi.

OpenRig has a feature called 'refocus' that tracks the chain of intent at each level and sends that intent chain to agents after compression or at intervals to check whether they are aligned with the bigger picture