← All Products
SuperLocalMemoryLIVE

Governed Memory for AI Agents

SuperLocalMemory 4.0 gives AI agents a governed local-first memory control plane. It combines durable memory transactions, scoped access, evidence-led retrieval, auditable operations, and CLI, MCP, dashboard, and framework-adapter surfaces. The V4 paper and implementation are public.

$npm install superlocalmemory
Read the Paper →GitHub →Website →
5,117+
Monthly Downloads
4
Public arXiv Preprints
CLI + MCP
Agent Surfaces
A / B / C
Operating Modes

Features

Reliability Spine

Generation-fenced admission, policy registration, verifiable memory transactions, projection ownership, and hash-checkable completion manifests.

Evidence-Led Retrieval

Dense, lexical, temporal, associative, and spreading-activation candidate producers fuse through one governed retrieval path.

Scoped Memory

Personal, named-profile, shared, and global scopes with role-aware access, provenance, export, and verified erasure.

Explicit Operating Modes

Mode A local core, Mode B local model, and Mode C deliberate external provider usage with explicit network behavior.

CLI, MCP, Dashboard, and Adapters

Operate the same memory system from agent tools, terminal workflows, the dashboard, and framework adapters.

Learning and Cache Paths

Feedback-driven learning, reusable retrieval paths, and context compression help agents retain useful context locally.

Use Cases

Persistent memory for Claude Code sessions
Cross-session context for any AI agent
Privacy-preserving enterprise agent memory
Research experiment tracking and recall

Research Paper

SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents

Varun Pratap Bhardwaj, 2026

Read on arXiv
Licensed under AGPL-3.0