Source: Letta documentation, memory blocks and archival memory

Letta's docs on in-context memory blocks (label, description, value, limit, read_only, shared), searchable archival memory and conversation search.

Contents

Summary

Letta organises agent memory as editable blocks pinned into the context window, plus an out-of-context archival store the agent searches with tools, plus automatic search over past messages. All state (messages, memories, tool calls) is persisted in a database, so evicted messages remain retrievable.

Key claims

  • A block has a label, a description (what the agent relies on most to decide how to use it), a value, a character limit, and an optional read_only flag.
  • Attached blocks are prepended to the prompt in a <memory_blocks> section showing description, current/limit character counts and value; they never need retrieval.
  • A block can be attached to several agents; one update is visible to all of them (shared memory). Setting value replaces the whole block, so concurrent writes are last-write-wins. The docs give no default limit.
  • Archival memory is semantically searchable, effectively unlimited, taggable, and cannot be pinned in context. Tools: archival_memory_insert and archival_memory_search (tag filter, pagination).
  • Guidance: blocks for always-visible, frequently changing information; archival for documents, logs, reports and history. Archival is curated by the agent; conversation search retrieves what was said automatically.
  • Letta’s newer docs describe “dreaming”: background subagents that review recent conversations and consolidate memory without blocking the active agent. Triggers are off, every N user messages, or on context compaction. Dreaming in Letta Code is distinct from the older, experimental server-side sleep-time agents.

Feeds

Agent memory

Suggest changes →