PlexusHive¶
Formats and tools for coordinating long-lived coding agents: the role each agent plays, the decisions that bind them, the status reports they file, and the envelope they put on messages to each other.
When a dozen agent sessions each work for days across hundreds of repositories, the human operator ends up as the only router and the only memory. PlexusHive writes down what each agent is for, where it works, who settles conflicts in a repository, and why things were decided, in plain JSON files that every agent can read and tests can validate.
Principles¶
- Roles, not sessions. A role is durable. The session playing it
declares it with
HIVE_ROLE, so renaming or restarting a session changes nothing in the records. - Stewards, not owners. Several roles may work in a repository; at most one stewards it and settles conflicts.
- An append-only decision log. Decisions are superseded, never rewritten.
- Go types are the source of truth. JSON Schemas are generated from them, and loading is strict, so a typo fails instead of being dropped.
- Your records stay yours. This module holds the formats and code; the records live in a hive directory of your own, usually a private repository.
At a glance¶
my-hive/
├── roles/<name>.json one file per role
└── decisions/<id>.json the append-only decision log
plexushive -C my-hive validate # check every role and decision
plexushive -C my-hive roles github.com/example/web # who works there, steward first
plexushive -C my-hive brief # decisions, blockers and status