Commands at a glance
What the agent remembers
OpenSRE keeps durable knowledge across sessions so you never repeat yourself:- Who you are — your name, role, and how you like to work
- Your infrastructure — cluster names, naming conventions, known-flaky services
- Your preferences — report formats, notification choices, defaults
- Investigation learnings — root causes and lessons worth keeping
Saving memories
Just tell the agent — no special syntax needed:Viewing and deleting memories
/memory forget prod-cluster-conventions, or ask the agent:
“forget what you know about the prod cluster”.
Where memories live
Memories are plain markdown files under~/.opensre/memory/ — one file per
memory plus a generated MEMORY.md index. They are stored locally and
unencrypted. The agent includes the memory index, and sometimes recalled
entries, in prompts sent to your configured LLM provider so it can use those
facts in future answers. You can open, edit, or delete the files directly at
any time; the index rebuilds on the next write.
Turning memory off
The session-end extraction makes one lightweight LLM call per session and
saves at most five memories. On shell exit that pass runs to completion after
resources are released so durable facts are not dropped. Never share secrets
or credentials expecting them to be remembered — the memory ingestion path
blocks obvious tokens, passwords, private keys, and credential-shaped values,
and redacts matching spans before the extraction LLM call.
Gateway (Slack / Telegram)
Memory is a host-global local folder. On a shared gateway host it is off by default so one allowlisted user’s facts cannot appear in another user’s prompts or channel replies. Single-operator gateway deployments can opt in withOPENSRE_MEMORY_GATEWAY_ENABLED=1.