WorkMATe
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0316453
Kruijne et al. RL-learned gating policies open/close multiple working-memory slots independently. Handles hierarchical 12-AX task with multiple concurrent context levels; all-or-nothing slot updates.
At a glance
- Type
- Bio-inspired RL-gated memory slots
- Tier
- T3
- Created
- 2021-01 (Neural Computation 33(1):1-40; published January 2021)
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- not applicable — not commercial
- Funding
- not applicable — not commercial
Taxonomy
- storage
- kv-cache
- retrieval
- attention
- persistence
- session
- update
- agent-controlled
- unit
- kv-token
- governance
- n/a
- conflict
- n/a
When to use
Optimised for: not applicable - research paper
Anti-fit: not applicable - research paper
Pros & cons
Pros
Explicit working-memory framework with managed buffer.
Cons
Research-stage; less popular than implicit context-window approaches.
Claims & capabilities
Working memory model with complex gated memory stores for sensory stimuli updated all-or-nothing; output module gates whether stimuli are encoded or discarded; comparison model in PLOS ONE study, where authors note WorkMATe stored stimuli override previous content making memorize/forget less flexible than RECOLLECT
Technical surface
- API surface
- not applicable — research paper
- Backend storage
- not applicable — research paper
- Deployment
- not applicable — not a deployable product
- 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 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.