Research Domain
Agentic Intelligence
Remy — the D-CSIL Lab Rat — a production terminal agent with a deterministic policy engine, reversible git-backed checkpoints, and durable memory. It replaced the earlier Hermes and OpenClaw agents.
OBSERVEDCURRENT EVIDENCE LEVEL
Research Question
Can an autonomous engineering agent be safe, auditable, and reversible by construction rather than by model goodwill?
Remy's design pushes safety out of the model and into the system: allow/deny policy rules the model cannot rewrite, git-backed snapshots for every file edit, an inspectable tool timeline, and SQLite session persistence.
It routes across OpenAI, Anthropic, and local model endpoints, and is reachable over Telegram, email, and Messenger. Its 'Soul' layer gives Remy identity, mood, and whisker nudges.