Log inSubmit server

Hidden while we check this listing

Our automated checks found a problem, so this listing is out of search, browse and the API until it clears. It comes back on its own once the problem is fixed.

  • The install package comes from a different repo than this listing's
Own this project? Claim it
Superlocalmemory logo

Superlocalmemory

Local-first MCP memory with governed recall, knowledge graphs, hybrid search, and 17+ tools for AI agents.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Superlocalmemory

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "superlocalmemory": {
      "command": "uvx",
      "args": [
        "superlocalmemory"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

The superlocalmemory MCP server gives AI agents persistent, local-first memory across sessions using structured facts, knowledge graphs, and hybrid retrieval. It exposes memory operations through MCP, including remembering and recalling information, while applying access controls, temporal filtering, auditability, and answer checks. Core remember and recall can run without model-provider calls in Mode A; choose it when agents need shared, inspectable memory that can abstain instead of confidently returning an unrelated result.

Use cases

  • Persist decisions and rules across agent sessions
  • Recall project facts with time-aware queries
  • Restrict memory access by workspace and scope
  • Audit, correct, and erase stored memories
  • Coordinate memory across parallel agents

Key features

  • Local-first persistent agent memory
  • Hybrid search with knowledge-graph support
  • Answer checking with abstention
  • Workspace roles and scoped access
  • Temporal recall and correction workflows
  • MCP tools for cache and reversible compression

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

8/8 checks healthy over the last 45d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 6d ago via OSV.dev · superlocalmemory (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars255Stargazers on the source repository.
Last commit1d agoMost recent push to the default branch.

How Superlocalmemory works

What superlocalmemory MCP server does

The superlocalmemory MCP server provides persistent memory for agents that otherwise lose context when a session ends. It stores facts such as decisions, rules, corrections, and project information, then retrieves relevant entries through MCP tools and the command-line interface.

The system combines knowledge-graph relationships with hybrid search. Retrieval uses multiple channels, result fusion, and a learned ranker rather than relying only on vector similarity. Memories also retain event time and learning time, allowing queries about what was true at a particular point or what the system knew before a date.

Access is organized around workspaces, roles, and personal, shared, or global scopes. The material describes default-deny cross-profile recall, retention rules, HMAC-verifiable erasure receipts, and a hash-chained audit log. Agent identity is recorded for writes, and trust scoring is used to address potentially harmful memory contributions.

How it works

The superlocalmemory MCP server can run in Mode A, where core remember and recall operations make no model-provider call. The software runs locally on Windows, Linux, and macOS, and does not require Docker, a graph database, or an API key. Data leaving the machine is described as an explicit choice rather than a requirement of core retrieval.

When an agent recalls information, an answer-check stage evaluates whether the returned memories actually address the question. Laya performs that check locally on a Mac, while Jev runs online on Windows, Linux, and macOS. If the retrieved material does not answer the question, recall can report an abstention instead of presenting an unrelated memory as an answer.

The system can learn from retrieval outcomes. A Thompson-sampling bandit adjusts channel weights, and a LightGBM ranker uses reported outcomes. New rankers undergo a shadow comparison before promotion and can be rolled back when the documented NDCG@10 threshold is missed.

Setup and configuration

Install the package with npm globally or with pipx. The documented npm route requires Node 18 or later and Python 3.12 or later; the pip route uses an activated Python virtual environment. After installation, run slm setup and select a mode. The command slm connect <client> connects the installation to a supported MCP client, such as Cursor or Claude Code.

A repository-based installation is also documented through platform-specific shell scripts for macOS, Linux, and Windows. The application supports all three operating systems.

Tools and capabilities

The superlocalmemory MCP server exposes 17 or more AI tools through MCP. The documented core operations include:

  • Saving memories with categories such as decisions, rules, facts, and corrections.
  • Recalling memories with ranked results and optional kind filters.
  • Replacing an existing fact and reviewing or rolling back that correction.
  • Querying memories by validity time or knowledge date.
  • Applying access scopes, retention rules, erasure workflows, and audit records.
  • Sharing messages, locks, and state between parallel agent sessions through SLM-Mesh.
  • Using exact caching and reversible compression through MCP tools or a skill.
  • Repeating bounded tasks until an independent test, schema, or linter gate passes, with each attempt recorded.

Limitations and notes

Search scores indicate ranking, not probability. Recall may show Incomplete search while the embedding model is loading. Answer checking depends on the selected judge: Laya is local to Mac, while Jev is online.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Superlocalmemory

superlocalmemory is an MCP server that connects AI agents to persistent local-first memory on the user’s machine. Its main tools let agents remember and recall facts across sessions, with hybrid search, knowledge-graph support, access controls, temporal queries, correction workflows, and answer checks that can abstain when stored memories do not answer a question.

Install it with `npm install -g superlocalmemory` or `pipx install superlocalmemory`, then run `slm setup`. The documented npm route requires Node 18+ and Python 3.12+. A virtual-environment pip installation and platform-specific repository install scripts are also available.

Yes, superlocalmemory documents Cursor as a supported client. After setup, run `slm connect cursor` to connect it. The README also names Claude Code, Codex, Windsurf, Zed, and VS Code or Copilot among its editor and agent integrations.

No, the documented installation requires neither an API key nor a graph database. It also does not require Docker. In Mode A, core remember and recall make no model-provider call, and the software runs on Windows, Linux, and macOS.

Yes, its answer-check stage evaluates whether retrieved memories answer the query and can return an abstention instead of a confident unrelated result. Laya performs this check locally on Mac, while Jev runs online on Windows, Linux, and macOS.

Related MCP servers

All in Knowledge & Memory All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewSuperlocalmemory AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/superlocalmemory?style=directory)](https://allmcps.com/mcp/superlocalmemory)
HTML Embed
<a href="https://allmcps.com/mcp/superlocalmemory"><img src="https://allmcps.com/api/badge/superlocalmemory?style=directory" alt="Superlocalmemory on AllMCPs" /></a>