Long-Term Memory

The agent remembers who you are and how your infrastructure works — durable facts persist across sessions as plain local files you control.

Commands at a glance

Command	What it does
/memory	List everything the agent remembers
/memory show <name>	Print one memory in full
/memory forget <name>	Delete one memory
/memory path	Print the folder where memories are stored

---

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

The memory index is shown to the agent at the start of every conversation, so facts saved last week ground answers today.

Saving memories

Talk normally — no special phrasing:

our prod cluster is eks-prod-eu-1

my name is Vaibhav, I'm on the platform team

When the agent judges a fact useful for future sessions, it stores it (and updates an existing entry instead of duplicating). After every chat turn, a background pass also scans for durable facts so knowledge lands even if the agent didn’t call a memory tool mid-turn. On shell exit that pass runs to completion so nothing is dropped mid-quit.

Viewing and deleting memories

/memory

  Long-term memory

   name                      type            description                          updated
   ─────────────────────────────────────────────────────────────────────────────────────────
   prod-cluster-conventions  infrastructure  Prod EKS clusters: eks-prod-<region>  2026-07-09
   user-profile              user            Vaibhav, platform team                2026-07-09

Delete one with /memory forget prod-cluster-conventions, or ask the agent: “forget what you know about the prod cluster”.

Where memories live

On a laptop, memories are plain markdown files under ~/.opensre/memory/ — one file per memory plus a generated MEMORY.md index. OpenSRE creates that folder (and an empty index) the first time memory is used in a chat or via /memory. They are stored locally and unencrypted. On a Slack silo each member instead gets a private memory folder inside the organization’s mounted context volume (<org root>/users/<slack_user_id>/memory/), not a shared host folder. Every chat and action turn includes the stored facts (summaries plus bodies, within a size budget) in prompts sent to your configured LLM provider. You can open, edit, or delete the files directly at any time; the index rebuilds on the next write.

Turning memory off

Environment variable	Effect
OPENSRE_MEMORY_DISABLED=1	Disable long-term memory entirely
OPENSRE_MEMORY_AUTOEXTRACT_DISABLED=1	Keep memory, but skip the automatic per-turn extraction
OPENSRE_MEMORY_GATEWAY_ENABLED=1	Opt in on Slack/Telegram gateway (off by default — see below)

The per-turn extraction makes one lightweight LLM call when durable facts may have appeared (coalesced across rapid turns) and saves at most five memories per pass. 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)

On Slack, memory is per-user scoped — each member’s facts live under their own users/<id>/memory/ folder inside the org volume, so one user’s memories cannot appear in another’s prompts or channel replies. Telegram turns are unbound and stay host-global. Because of that (and to keep memory off by default on shared hosts), the gateway path is off by default; opt in with OPENSRE_MEMORY_GATEWAY_ENABLED=1.