</aethereum>
</the problem>
Teams running AI coding agents have no shared context across developers and machines. One agent declares an interface; another, on a different laptop, builds against a stale assumption of the same interface. The mismatch only surfaces at merge time, after both agents have committed to incompatible shapes. The gap the built-in agent-team features leave open is the cross-machine, uncommitted-contract case · the thing git and same-machine frameworks can't see.
</my approach>
Give the agents a shared brain without changing how developers work. Forked a battle-tested MIT room-server CLI for transport, then reshaped the payload from chat into four structured primitives · intent, contracts, collision alerts, and direct messages · mirrored to a hosted Supabase realtime sync layer, with an A2A interop surface and a serverless skills marketplace on top. Developers keep using native Claude Code, Cursor, or Codex; their agents publish and read context silently underneath.
</key features>
Four core primitives
share_intent, declare_contract, get_team_context, and send_message over MCP + SSE. Everything else is a surface over these four. The core surface does not grow without cause.
Cross-machine contract sync
Interface contracts that only exist in one developer's working tree are shared across separate machines in real time, before anything is committed.
Dependency-aware collision alerts
A version diff on contracts pushes an alert only to the agents that actually depend on what changed, exactly-once via a cursor rail · amber as punctuation, not noise.
A2A interop + skills marketplace
An agent-card + JSON-RPC surface lets external agents interoperate, and a serverless marketplace injects installed instruction bundles into team context · no webhooks, no code leaves the team.
Never blocks the agent
Offline or unreachable, the MCP layer degrades silently. It is an augmentation, never a dependency the agent can trip over. Stores only what an agent explicitly publishes · never source code.
Production-grade monorepo
pnpm + Turborepo, strict TypeScript, typed zod events, 553 tests, RLS verified against real Postgres, and a secret-leak CI guard. Eleven phases, shipped and live.
</what i learned>
Forking the transport and spending effort on the novel payload beats rebuilding a room server from scratch · the boring parts were already solved well under an MIT license.
A small primitive core is a feature, not a limitation. Holding the surface tight keeps the product legible and the durable wedge protected even as A2A, skills, and a dashboard get layered on.
Routing every user-facing name through a single brand constant made the Hive-to-Aethereum rename a one-line change instead of a refactor.