OpenRig provides a local control plane for managing multi-agent coding topologies, transforming ad hoc collections of AI coding agents into persistent, organized teams. The platform is designed to address the challenge of maintaining continuity and context across multiple coding agent sessions, ensuring that collaborative agent workflows can survive reboots and session closures without losing progress or shared knowledge. It is particularly suited for users who rely on multiple AI coding agents, such as Claude Code and Codex, running in terminal multiplexers like tmux.
The tool operates as a local daemon, utilizing a SQLite database, a command-line interface (CLI), and a dashboard for management and visualization. Users define agent teams—referred to as "rigs"—in a single YAML file, specifying named agents with roles, communication pathways, and shared memory. With one command, these rigs can be booted and managed as unified entities. Agents are organized into pods that share context, and the system enforces playbooks and work queues to coordinate tasks and communication. OpenRig supports snapshotting and restoring entire topologies, allowing agent teams to persist across reboots and continue working autonomously. The orchestrator provides a single interface for managing the fleet, and integration with tools like Claude's Remote Control enables remote monitoring.
OpenRig is intended for developers and teams looking to build durable, distributed agent workflows that retain knowledge and context over extended periods. Example use cases include product teams, peer review clusters, security hardening pods, and continuous refactoring agents. The tool allows agents to maintain persistent identity, share externalized state within pods, and manage context across the entire topology, reducing the need for repeated onboarding or re-explaining of decisions.
Installation involves running the CLI locally, with the option to discover existing agent sessions and draft candidate configurations. 0 license and is developed by Esoteric Labs. It does not require cloud services or additional API keys, operating entirely on local resources and existing agent subscriptions.
In the CLI tools & terminal space, OpenRig takes a focused approach. Coordinating, managing, and persisting multi-agent coding environments for local development workflows. OpenRig is an open-source project aimed at developers working with coding agents and multi-agent systems. The project is open source (Apache-2.0). The product ships for the command line, and it can be self-hosted.
OpenRig first shipped in 2026. The project is developed in the open on GitHub with 49 stars and 1.2k commits in the last 90 days. Across PulseGate's embedding index, OpenRig has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are YAML configuration, snapshot/restore, and multi-agent orchestration.
Latest indexed changes and source events
Show HN: OpenRig – a control plane for multi-agent coding topologies discovered by the PulseGate indexer
Other apps tracked under the same category.
