This is a useful direction, especially for teams that mix Codex and Claude in the same repo.
One thing that matters in practice is memory lifecycle. Shared memory tends to drift unless entries have retention rules (TTL, dedupe, and merge policy) plus periodic compaction.
Are you planning a policy layer so users can control what persists as raw events versus summarized state?
I use both OpenAI Codex and Claude Code daily on the same codebase. The biggest pain — they don't share memory. Claude fixes a bug, Codex repeats it next session. Every session starts from zero.
So I built Open Timeline Engine — a local-first engine that captures your decisions, mines patterns, and gives any MCP agent shared memory.
One thing that matters in practice is memory lifecycle. Shared memory tends to drift unless entries have retention rules (TTL, dedupe, and merge policy) plus periodic compaction.
Are you planning a policy layer so users can control what persists as raw events versus summarized state?
reply