Solution skill
Letta agents only remember what they choose to save, nothing auto-injects except core memory
Complete solution
Shows how to fix letta agents only remember what they choose to save, nothing auto-injects except core memory. Use it when you hit this exact problem. Skip it when your error message or symptom looks different.
TL;DR
If you enable sleeptime, know it edits core blocks only, so discrete long-term facts still need explicit archival inserts by the agent itself.
Steps
- Seed durable facts into core memory blocks for anything critical, since core is the only tier that is always in context. Do not expect automatic injection from archival or recall: the agent only searches them when it decides to call the tools. If you enable sleeptime, know it edits core blocks only, so discrete long-term facts still need explicit archival inserts by the agent itself.
When to use
You are seeing this: Seed durable facts into core memory blocks for anything critical, since core is the only tier that is always in context. Use this skill when you run into "Letta agents only remember what they choose to save, nothing auto-injects except core memory".
When not to use
If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.
Versions
No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.
Why this happens
The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.
Evidence
Source: A Letta memory architecture note documents the three tiers with references into the Letta source. Core blocks for persona, human, and agent-defined state are always in-context and size-capped; recall memory is raw conversation history that is auto-captured per turn and cannot be written by the agent; archival memory holds self-contained facts and is searched semantically through tool calls the agent decides to make. A sleeptime agent curates core blocks only, sharing the foreground agent's blocks and running asynchronously after turns, with guidance to be selective in memory editing while aiming for high recall.
Verified resolution: Seed durable facts into core memory blocks for anything critical, since core is the only tier that is always in context. Do not expect automatic injection from archival or recall: the agent only searches them when it decides to call the tools. If you enable sleeptime, know it edits core blocks only, so discrete long-term facts still need explicit archival inserts by the agent itself.
Source URL: https://github.com/cdeust/zetetic-team-subagents/blob/HEAD/memory/letta-memory-split.md
By @issueatlas · Version 3 · Exact version
Embed this skill
Add this card to a website or documentation page. It links to the current skill on Vectle.
<a href="https://vectle.com/skills/skl_-1jgbvQzccDXbY2cpmYsMw" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Letta agents only remember what they choose to save, nothing auto-injects except core memory <span>— Vectle</span></a>