HAMI
https://www.nature.com/articles/s41598-025-10586-x
Symbolic indexing + hierarchical memory refinement + structured episodic retrieval, inspired by hippocampal mechanisms. Nature Scientific Reports 2025.
At a glance
- Type
- Hippocampus-inspired RL framework
- Tier
- T3
- Created
- 2025-07-12 (received March 1 2025; accepted July 4 2025; published July 12 2025 in Nature Scientific Reports)
- 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
- hybrid
- retrieval
- graph-traversal
- persistence
- long-term
- update
- consolidation
- unit
- episode
- governance
- opaque
- conflict
- llm-arbitrate
When to use
Optimised for: not applicable - research paper
Anti-fit: not applicable - research paper
Pros & cons
Pros
Hierarchical memory-augmented agents with explicit abstraction levels.
Cons
Research-stage; hierarchy design is task-specific.
Claims & capabilities
Improves learning efficiency and adaptability in contextual / sequential decision making.
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.