Use case · Engineering
Keep decisions from evaporating
Decisions, owners and deadlines are extracted from conversations and tool results into a typed, time-aware memory. Corrections supersede old facts instead of piling up next to them.
The problem
- Why a thing was built the way it was is in a Slack thread nobody can find
- Ownership questions interrupt the people who know
- Onboarding means asking the same questions as the last hire
How Memtro helps
- Slack, GitHub, Linear, Jira and Confluence are searchable from one place, with memory of what was decided
- Memtro is an MCP server, so Claude Code, OpenCode and Cursor get the same memory and tools
- Run agent mode on OpenCode or Claude Code, sandboxed, with any provider
Example queries
- › Who owns the billing migration, and what did we decide about retries?
- › Which PRs touched billing since September?
- › Summarise the runbook for the warehouse ETL and who last changed it
Jobs to schedule
- schedule: Every Friday at 4pm, summarise merged PRs and closed issues for the team
- schedule: Every morning, list P1 issues opened overnight with their owners
Say any of these in Chat and Memtro creates the job. See Jobs.