AI & ML interests

Mnemoverse — persistent memory API for AI agents. Memory that learns from outcomes (Hebbian associations + prediction-error feedback), grades recall by recency, and consolidates — one key across Claude, Cursor, VS Code & ChatGPT. Docs: mnemoverse.com/docs

Recent Activity

Organization Card

Mnemoverse

Persistent, cross-tool memory for AI agents.

Mnemoverse gives agents a shared memory layer they can use across Cursor, Claude Code, VS Code, and other MCP-compatible clients. It is designed for facts, decisions, preferences, lessons learned, and other context that should survive beyond a single chat or tool.

Start here

What we work on

  • persistent memory for long-running agents
  • retrieval shaped by importance, recency, and feedback
  • semantic and relational memory structures
  • temporal context, provenance, and conflicting memories
  • evaluation and benchmarks for agent memory
  • knowledge graphs and controllable levels of abstraction

Research

Semantic Level of Detail for Knowledge Graphs: Discovering Abstraction Boundaries via Spectral Heat Diffusion

Agent Memory: Structure, Time, and Evaluation is a curated research map covering temporal change, structured representations, abstraction, consolidation, and evaluation.

Agent Memory Evaluation Map lets you explore public research by evaluation target, compare evidence and limitations, and export a checklist in Markdown or JSON. It is a research navigator, not a product benchmark or leaderboard. An exported checklist is an evaluation plan, not a record of tests run.

Status

Mnemoverse is under active development. If you are evaluating memory systems for an agent workflow, the documentation is the best place to begin.

models 0

None public yet

datasets 0

None public yet