Sleep-time Compute (Letta)

https://letta.com/blog/sleep-time-compute

Agents use idle time to reorganize and pre-reason over stored context ('learned context'). Letta ships this as sleep-time agents (v0.7.0+), where a background agent manages the primary agent's core memory. Traction: Shipped in Letta 0.7.0 and Letta Code (/sleeptime); arXiv 2504.13171. Letta's current source moved to letta-ai/letta-code; the V1 API server (where sleep-time agents first shipped) is retired to the letta-ai/letta archive branch. Letta Code's README now calls sleep-time compute 'dreaming': periodic dreaming via /sleeptime, manual /dream and /reflect, plus server-side dreaming.

Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 13 cited facts, 1 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Type
Paper vendor fix
Tier
T3
Created
2023-10-11 repo fix
Pricing
searched not found fix
Funding
searched not found fix
Freshness
2026-10-29 fix
Layer
agent-infra repo fix
Licensing
open-source repo fix

Memory taxonomy

storage
kv
retrieval
injection
persistence
long-term
update
consolidation
unit
summary
governance
inspectable
conflict
llm-arbitrate

When to use

Optimised for: searched not found

Anti-fit: searched not found

Pros & cons

Pros

searched not found

Cons

searched not found

Claims & capabilities

BRIEF Sleep-time compute is a new way to scale AI capabilities: letting models "think" during downtime. Instead of sitting idle between tasks, AI agents can now use their "sleep" time to process information and form new connections by rewriting their memory state. Read our research paper here , and learn how to make sleep-time agents in Letta on our docs .

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
searched not found
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
searched not found
A2A
searched not found
OpenTelemetry
searched not found

Similar systems

Other recent method papers — theorized, no distinct product in the catalog, ranked by inbound references.

  • Compressive Transformer T3

    Maintains recent states in full resolution while compressing older memories with learned compression functions. DeepMind.

  • MemGPT v2 / agent-tools T3

    Already in catalog as the foundational MemGPT paper. Note: Letta is the productionised successor (cross-listed).

  • Transformer-XL T3

    Extends context through segment-level recurrence + caching of hidden states from prior segments. Foundational long-context architecture.

  • Generative Agents T3

    Park et al. — landmark agent-simulation paper. Reflection + memory stream + retrieval enable believable agent behavior.

  • MemoryBank T3

    Enhances LLMs with long-term memory. Early influential paper.

  • Reflexion T3

    Language agents with verbal reinforcement learning.

Sources (12 cited facts, 1 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-29
    • License “Apache-2.0 (Letta)” → “Apache-2.0 (Letta Code)” source
    • Latest release “last commit 2026-10-18” → “Letta Code v0.34.30 (npm @letta-ai/letta-code, 2026-10-29)” source
    #307
  2. 2026-10-23 Added to the catalog #222