Tools Categories Trending New Compare

RAG / Knowledge Base/

superlocalmemory

superlocalmemory

Active·★ 160·AGPL-3.0·Updated 2026-05-27

★ Trending★ RAG / Knowledge Base★ Memory & Context

World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on LoCoMo. No cloud, no APIs, no data leaves your machine. Additionally, mode C (LLM/Cloud) - 87.7% LoCoMo. Research-backed. arXiv: 2603.14588

SuperLocalMemory V3 is a local-first AI agent memory system that uses mathematical techniques (differential geometry, algebraic topology, stochastic analysis) to replace cloud LLM dependency. It offers three operating modes, achieves high benchmark scores, and is EU AI Act compliant.

#agent-memory#agent-reliability#ai-agents#claude-code#cursor#knowledge-graph#llm-memory#local-first

$ Install

$ npm install -g superlocalmemory

↗ Visit site ★ GitHub

01

Features

015-channel hybrid retrieval (Semantic, BM25, Entity Graph, Temporal, Hopfield)

02Auto-learned soft prompts and adaptive memory lifecycle

03Skill evolution with performance tracking

04Tiered storage (active/warm/cold/archived)

05Trust & Security (Bayesian trust scoring, ABAC, audit trail)

02

Compatibility

MCP

MCP Native

Verified via docs

CLI

CLI Native

Verified via docs

Claude Code

Claude Code

Verified via docs

Cursor

Cursor

Verified via docs

Windsurf

Windsurf

Verified via docs

VS Code

VS Code

Verified via docs

03

Quick start

1

$ npm install -g superlocalmemory

04

Use cases

↳IDE integration (Claude Code, Cursor, Windsurf)

↳CI/CD pipelines

↳Agent frameworks (OpenClaw, Codex, Goose)

05

Alternatives

mindsdb★ 39.2k

Federated Query Engine for AI - The only MCP Server you'll ever need

Brave Search MCP★ 86.5k

Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.

context-mode★ 16.0k

Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms

Auto-claude-code-research-in-sleep★ 11.0k

ARIS ⚔️ (Auto-Research-In-Sleep) — Claude Code skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation via Codex MCP

agents-best-practices★ 1.1k

Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.

The agent environment for long-horizon work, continuity, and self-evolution.

awesome-claude★ 250

HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.

initrunner★ 38

Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon

See all alternatives →

Related searches

superlocalmemory Alternatives Best RAG / Knowledge Base Tools 2026 Open Source RAG / Knowledge Base superlocalmemory Tutorial superlocalmemory Vs Competitors agent-memory agent-reliability ai-agents

Comments

Log in to leave a comment

S
Sutton ClarkMay 16, 2026
Good for privacy-conscious users who need memory without cloud storage.
R
Rebel DavisMay 13, 2026
Performance claims are specific and testable — not just marketing.
P
Phoenix JohnsonApr 20, 2026
Zero-LLM recall means memory retrieval doesn't consume API tokens.
H
Harper LewisMar 3, 2026
74% retrieval and 60% zero-LLM recall rates for local-only AI memory are impressive benchmarks.

On this page

01Features 02Compatibility 03Quick start 04Use cases 05Alternatives

Stats

GitHub Stars★ 160

Last commit3d ago

StatusActive

LicenseAGPL-3.0

CategoryRAG / Knowledge Base

Trend (30d)

+6.4↑ 0.8%

Links

Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.

QYS GitHub Buy me a coffee ☕

Browse by Category

Code Assistant Workflow Automation RAG / Knowledge Base Multi-Agent Browser Automation LLM Infra Dev Tooling Observability

Not affiliated with Anthropic, OpenAI or Microsoft.