// features
Core features
Everything you need to orchestrate AI coding without giving up control.
Orchestration vs execution
The Coordinator orchestrates and never writes code. Host CLIs execute and never decide. No coupling, no blurred responsibility.
01 / 8Container-as-role
9 team roles — PM, Architect, Frontend, Backend, QA, Security, DevOps — each in its own container, independently scalable and replaceable.
02 / 8A2A protocol collaboration
Structured inter-agent messaging. InProc mode for development, Redis Pub/Sub for containerized deployment.
03 / 8Deterministic quality gate
golangci-lint, go vet and go test run as a hard machine check. No relying on the model to grade itself.
04 / 8RAG + project memory
BM25 retrieval injects context. Memory accumulates failure lessons and historical solutions across runs.
05 / 8Four external protocols
gRPC for the TUI, MCP for external tools, ACP for standard Agent clients, A2A for cross-instance mesh.
06 / 8Local-first, keyless
Code stays inside the container. No API keys held. All authentication is delegated to the underlying host CLI.
07 / 8Scale-adaptive flow
A quick edit skips the DAG. A large project gets the full team. The platform adapts to the work, not the other way around.
08 / 8