01
Code Intelligence
Awareness and understanding for agents: a live map of code, symbols, impact, reuse, and prior work — selected per task, not retrieved by keyword.
Vision
Context into execution.
Rhei is the shared product system that turns context into execution. It holds feedback, intent, decisions, plans, and code, shapes that context into work, and helps humans and agents carry it all the way to production.
The system
02
Review Intelligence
Leverages code intelligence and agents so review keeps pace with agent output: impact, reuse, and proof gaps attached to every goal, diff, and PR.
03
Canvas Intelligence
Humans and agents working closer together: one spotlight-fast surface to find anything Rhei knows, steer work with it, and approve what ships.
CLI
Our own CLI to run agents where the context already lives — the repo.
Voice
Voice via mobile into the code intelligence cloud and cloud agents — ask about your codebase from anywhere.
Toward this vision, today we are launching:
beta · today
Code Intelligence over MCP
Local-first code map, working context, and memory for Codex, Claude Code, OpenCode, and internal agents.
beta · today
Rhei CLI
rhei init maps the repo, builds local intelligence, and connects your agents in one pass.
today
Context receipts
Every run shows what context was chosen, what was used, and why.
Roadmap
now
Code Intelligence
Local awareness over MCP: code map, working context, impact, and memory. In beta today.
next
Review Intelligence
Report-only review on goals, diffs, and PRs — impact, reuse, and proof gaps surfaced before merge.
ahead
Canvas Intelligence
A shared surface where humans steer agents — spotlight-fast across everything Rhei knows.
ahead
CLI agents & Voice
Run agents from the Rhei CLI. Reach the code intelligence cloud and cloud agents by voice, from your phone.