Catalog Systems Research / specialised systems BAI-LAB MemoryOS

BAI-LAB MemoryOS

https://github.com/BAI-LAB/MemoryOS

Hierarchical "OS" with Storage / Updating / Retrieval / Generation modules. Short-term → mid-term via FIFO dialogue-chain; mid-term → long-term via segmented paging.

Active · Verified 2026-10-28 · fresh as of 2026-10-28 · 26 cited facts, 1 with a third-party source · Suggest a correction

At a glance

Type
Hierarchical: short / mid / long-term repo fix
Tier
T3
Section
Research / specialised systems
Created
2025-05 repo fix
Latest release
V1.2 2025-07-18 repo fix
License
Apache-2.0 repo fix
GitHub
1.4k★ +40/mo Python repo fix
Pricing
searched not found fix
Funding
not applicable — not commercial fix
Freshness
2026-10-28 fix
Layer
agent-infra repo fix
Licensing
open-source repo fix
Developer activity
OpenRank 0.45 (12-mo avg 2.69) · 2 participants — 2026-05 third-party fix
Maintainer health
0 issues in 90 days · 0 releases in 12 months (latest 2025-07-18) · bus factor 1 — as of 2026-10-31 repo

Memory taxonomy

storage
hybrid
retrieval
similarity
persistence
long-term
update
consolidation
unit
summary
governance
inspectable
conflict
n/a

When to use

Optimised for: research positioning (see memory_model)

Anti-fit: not applicable - research paper

Pros & cons

Pros

ICML 2025 venue — peer-reviewed memory-as-OS framework.

Cons

Research scope; smaller community than commercial memory layers.

Claims & capabilities

EMNLP 2025 Oral. +48.36% F1 and +46.18% BLEU-1 over baselines on LoCoMo with GPT-4o-mini.

Technical surface

API surface
not applicable — research paper
Backend storage
not applicable — research paper
Deployment
searched not found
Embedding model
not applicable — research paper
Multi-tenancy
not applicable — research paper
MCP
not applicable — research paper, no deployed product
A2A
not applicable — research paper, no deployed product
OpenTelemetry
not applicable — research paper, no deployed product

Similar systems

Other research / specialised systems in the catalog, ranked by inbound references.

  • A-MEM T3

    Treats memories as atomic linkable notes — explicit nod to Zettelkasten knowledge management. Dynamic linking; retroactive memory revision.

  • Titans (Google) T4

    Neural long-term memory module that learns to memorise at test time. Uses gradient-of-loss as "surprise" signal; adaptive weight-decay forgetting. Three variants: MAC (memory-as-context), MAG (memory-as-gate), MAL (memory-as-layer).

  • EverMemOS T4

    Self-organizing memory OS for structured long-horizon reasoning. Three-phase model: episodic, semantic, reconstructive.

  • EVOLVE-MEM T3

    Dynamic Memory Network + Hierarchical Memory Manager + Self-Improvement Engine. L0 raw embeddings, L1 contextual summaries, L2 high-level principles. NeurIPS 2025 (Scaling Environments for Agents workshop).

  • LiCoMemory T4

    Lightweight hierarchical graph (CogniGraph) with entities and relations as semantic indexing layers. Incremental graph construction, fast updates, low-latency inference. Nov 2025.

  • MemoRAG T3

    RAG framework on top of a long-context memory model. Builds global memory once, generates contextual clues at query time. TheWebConf 2025.

Sources (25 cited facts, 1 third-party)

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

Related systems

References (1)

  • A-MEM cites — S2 isInfluential citation

Referenced by (4)