SuperLocalMemory Logo
SuperLocalMemory
OPEN RESEARCH • MIT LICENSE

Production-Grade
Agent Memory
at Scale

Mathematical foundations for AI agent memory systems that scale. 74.8% on LoCoMo with data staying local — the highest local-first score reported. EU AI Act compliant by architecture. Open source.

Get Started Read the Paper
74.8%
Local-first retrieval
87.7%
Full power (Mode C)
60.4%
Pure zero-LLM
17+
IDE integrations
superlocalmemory
SCROLL
NEW RELEASE

V3.2: The Living Brain

Recall in <10ms. Memory that organizes itself.

Your AI Agent Remembers Everything

⚡

100x Faster Recall

sqlite-vec KNN search replaces full-table scan. Sub-10ms retrieval across tens of thousands of memories.

🔍

Automatic Surfacing

Memories surface proactively based on context. Your agent receives relevant knowledge without explicit queries.

🌐

Multi-Hop Reasoning

Spreading activation traverses the memory graph to find non-obvious connections across distant nodes.

⚙

Self-Organizing

Idle-time consolidation compresses, merges, and compiles memories. The graph improves without manual curation.

Read the Documentation Read the Paper

Open source, MIT licensed. A Qualixar Research Initiative.

The Problem

The Context Persistence Problem

01

Session Reset

No Persistence.

Current AI assistants lack persistent memory across sessions. Context accumulated during a session is discarded at termination.

02

Context Loss

Re-initialization Required.

Domain-specific patterns and decisions require re-initialization each session. Learned preferences do not transfer.

03

Architecture Trade-offs

External Dependencies.

Centralized memory introduces external data dependencies and privacy considerations for sensitive development contexts.

There's a better way ↓
The Architecture

9 Layers Deep

Each layer handles one responsibility. Together, they give your AI persistent, intelligent memory.

Explore full architecture →
Capabilities

Neural Capabilities

Every feature designed to make your AI smarter, faster, and completely private.

Knowledge Graph

Automatic entity extraction, relationship mapping, and concept linking. Your AI understands how ideas connect.

Learn more

17+ IDE Integrations

Claude Code, Cursor, VS Code, Windsurf, JetBrains, Zed, and more. 27 MCP tools. One memory across all your tools.

Learn more
NEW

Active Learning

V3.1: Memory that learns. Every recall trains the system. 3-phase progression from baseline to ML model — at zero token cost.

Learn more

Privacy First

100% local. Zero cloud. Your memories never leave your machine. EU AI Act compliant.

Learn more

10.6ms Search

4-channel hybrid retrieval: semantic + BM25 + entity graph + temporal. Faster than a network round-trip.

Learn more

Multi-Agent Memory

Multiple AI agents share one memory layer. Profiles keep context separate. Trust scoring per agent.

Learn more

Memory Lifecycle

Self-managing lifecycle with confidence decay, consolidation, and deduplication. No manual cleanup needed.

Learn more

Behavioral Patterns

Detects your tech preferences, temporal patterns, and workflow sequences. Auto-captures decisions and bug fixes.

Learn more

Enterprise Compliance

Access control, immutable audit trails, and retention policies. Ready for GDPR, HIPAA, and EU AI Act.

Learn more
Live Demo

See It Think

Three commands. That's all it takes to give your AI persistent memory.

superlocalmemory — demo
LoCoMo Benchmark Results

Measured Performance

Evaluated on the LoCoMo benchmark (Long Conversation Memory). Mode A Retrieval achieves 74.8% — the highest score reported without cloud dependency.

0.0%
Mode A — Local Retrieval
Data stays on your machine
0.0%
Mode C — Full Power
Cloud LLM at every layer
0.0%
Pure Zero-LLM
No LLM at any stage
0.0pp
Math Layer Gain
Avg improvement

LoCoMo Benchmark: Competitive Landscape

EverMemOS (SOTA) 92.3%
MemMachine 91.7%
SLM V3 — Mode C (cloud LLM at every layer) 87.7%
SLM V3 — Mode A Retrieval (data stays local) 74.8%
SLM V3 — Mode A Raw (pure zero-LLM) 60.4%
Mem0 ($24M funded) ~58-66%

Mode A Retrieval (74.8%) is the highest score achieved without cloud dependency during retrieval.
Mode A Raw (60.4%) uses no LLM at any stage — a first in the field.
All other systems require cloud LLM for core operations.

Ecosystem

Everywhere You Code

One memory layer. Every IDE and AI tool you use.

Claude Code
Cursor
VS Code
Windsurf
Neovim
Vim
JetBrains
Zed
Continue
Cline
Roo Code
ChatGPT
Perplexity
Gemini CLI
OpenAI Codex
Copilot
Any MCP Client
View integration guides →
COMMON QUESTIONS

Frequently Asked Questions

What is SuperLocalMemory?

+
SuperLocalMemory V3 is the first agent memory system with mathematical guarantees. It uses information geometry (Fisher-Rao), algebraic topology (sheaf cohomology), and stochastic dynamics (Langevin) for retrieval, consistency, and lifecycle. 74.8% on LoCoMo with data staying local — highest local-first score. 87.7% in full power mode. Open source under MIT.

Which AI tools does SuperLocalMemory work with?

+
SuperLocalMemory integrates with 17+ tools including Claude Code, Cursor, VS Code Copilot, Windsurf, ChatGPT Desktop, Perplexity, Continue.dev, Zed, and more via the Model Context Protocol (MCP).

Is it open source?

+
Yes. SuperLocalMemory is published under the MIT license as part of our open research initiative. The source code, documentation, and research papers are publicly available.

How does the local-first approach differ?

+
Local-first architecture keeps all data on user infrastructure. This contrasts with cloud-hosted approaches that require external data transit. See our Research Landscape page for a detailed comparison of approaches.

How do I install it?

+
Install via npm (npm install -g superlocalmemory), then run slm setup. Choose your operating mode: Mode A (zero cloud), Mode B (local Ollama), or Mode C (cloud LLM). All Python dependencies install automatically.

Does SuperLocalMemory send data externally?

+
No. The architecture is fully local. All storage uses on-device SQLite databases with no external network calls or telemetry.

Does SuperLocalMemory work with CI/CD pipelines and agent frameworks?

+
Yes. SuperLocalMemory is the only AI memory system with both MCP (for IDE integration) and an agent-native CLI with structured JSON output. Every data-returning command supports --json for a consistent envelope with success status, data payload, and next_actions guidance. Works with GitHub Actions, n8n, Docker, shell scripts, OpenClaw, Codex, Goose, nanobot, and any tool that can call a CLI command.

What is the --json flag?

+
The --json flag enables structured JSON output on all 12 data-returning CLI commands (recall, remember, list, status, health, trace, forget, delete, update, mode, profile, connect). The response follows a consistent envelope: {success, command, version, data, next_actions}. This makes SuperLocalMemory agent-native — AI agents can parse the output reliably without text scraping. Use with jq for powerful shell pipelines: slm recall 'auth' --json | jq '.data.results[0].content'
Quick Start

Installation

getting started
# Install (one command — everything included) $ npm install -g superlocalmemory
# Setup — choose your mode (A/B/C) $ slm setup
# Store your first memory $ slm remember "Alice works at Google as Staff Engineer"
# Recall it later $ slm recall "What does Alice do?"
✓ V3 engine active. Mode A. 528 facts indexed. Math layers: Active.
Install Read the Docs

MIT License • Local-first architecture

Community

Community & Contributions

⭐
GitHub Repository
MIT
Open Source
OSS
Open Source
Join on GitHub