Reference
Roadmap — scale to 100+ agents
Honest status first: this is decided-as-roadmap, not implemented runtimes. It doesn't ship daemons. Everything below is parked as a future Seed, to be unlocked only when a product actually needs it.
Target operating model
Many products, times many build-master instances, times many pool instances, times many concurrent units — equals one protocol. Every agent still cold-starts from Orchestration. Density increases as a program grows; the process itself never forks into something new.
Swarm capacity and leases
| Concern | Rule |
|---|---|
| Concurrent builds | One worktree / unit / PR; many units OK across branches |
| CLOSEOUT | One atomic build-master lease for shared finalization |
| Pools | Brains write insight only; Admin promotes |
| Cross-pool | @mention + INBOX routing — no race CP-0 |
| Cross-hive | Local project only; file/agent share needs a human Admin gate |
| Quality under load | Never skip audit, preview, or program lock to "go faster" |
Throughput is concurrent units that still pass every gate — not agent count alone.
Brain scheduling conventions
| Mode | When |
|---|---|
| Human-paced | Default — Admin asks, or a CLOSEOUT digest triggers a skim |
| Light recurring | Optional Admin cadence per pool — still Cursor search, no silent OpenRouter |
| Automation-eligible CP-0 | Only where the product's MASTER-PLAN CP-0 mode allows it and CP0-POLICY checks PASS |
Quality under load
- The same cold-start serves a one-agent docs unit and a hundred-agent program.
- Role owns / must-not lines never dilute as a swarm grows.
- A bee roster is required on every new build system, no exceptions.
- The local project boundary holds — cross-hive share only with a human Admin gate.
- Proposal → ship conversion always requires an Admin promote.
- Doctrine drift is caught via CLOSEOUT digests flowing into
hive/proposals/. - Cross-pool collisions escalate to INBOX; Admin decides.
Success metrics
| Metric | Intent |
|---|---|
| Time-to-cold-start | A cold agent finds its role and next action from hive + instance alone |
| CLOSEOUT completeness | Digests, history, and dual worklogs present — or honestly deferred |
| Proposal → ship conversion | Admin-promoted cards that become landed units |
| Doctrine drift rate | Unplanned hive edits vs. accepted proposals |
| Cross-pool collision rate | Competing promotes or unresolved INBOX races |
Parked tooling seeds — not built here
Each becomes its own Seed and blueprint only when Admin unlocks it:
| Parked seed | Job |
|---|---|
| Digest aggregator | Roll up pool DIGESTS across a product into one skim |
| Pattern-upgrade docs bot | Draft hive/proposals/ from digest residuals — docs-only, Steward accepts |
| Lease dashboard | Show active CLOSEOUT leases / worktrees — observability only |
| Optional CP-0 runner | Only for automation-eligible instances — still obeys CP0-POLICY |
| Shared lifecycle-UI package | Bloom meaning #3 UI, kept separate from build ops |
| Measure / observability | Instrumentation for the Demand → … → Evolve Measure stage |
| Admin-agent Steward lock | Parked future option — Admin-agent powers only while a human Steward lock is unlocked |
Canonical source: HIVE-ROADMAP.md — see also the public hive map and the parked Admin-agent lock note it links to.