Memolet
https://doi.org/10.1145/3654777.3676388
Reifies the reuse of user-AI conversational memories. CHI/UIST.
At a glance
- Type
- User-AI conversational memory reuse
- Tier
- T3
- Created
- 2024-10 (UIST 2024 conference October 13-16 2024; arxiv preprint available prior)
- 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
- vector
- retrieval
- similarity
- persistence
- cross-session
- update
- append-only
- unit
- chunk
- governance
- user-controllable
- conflict
- manual
When to use
Optimised for: not applicable - research paper
Anti-fit: not applicable - research paper
Pros & cons
Pros
Lightweight memory unit abstraction — finer-grained than fact-extraction.
Cons
Research-stage; less adoption than fact-shaped memory layers.
Claims & capabilities
Reifies user-AI conversational memories as visible, reusable units; within-subjects study with two-phase protocol investigated four design guidelines: user interactions across reuse stages, recall/extraction patterns, externalised sensemaking organization, and intent-AI alignment
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.