Superlocalmemory

Long-term memory for OpenClaw that stays on your computer. Recall past decisions and save new ones with SuperLocalMemory.

278 stars 36 forksProductivity & Notes Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add qualixar/superlocalmemory

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add qualixar/superlocalmemory --skill superlocalmemory
Manual install
git clone --depth 1 https://github.com/qualixar/superlocalmemory.git /tmp/superlocalmemory
mkdir -p ~/.claude/skills
cp -r /tmp/superlocalmemory/clawhub-skill/superlocalmemory ~/.claude/skills/superlocalmemory

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# SuperLocalMemory

SuperLocalMemory (SLM) gives OpenClaw a memory that lasts across sessions and apps. Memories live in a SQLite database under `~/.superlocalmemory` on this computer. Nothing is sent anywhere unless the user turns on an optional cloud feature themselves.

The SLM engine is a separate open-source project (AGPL-3.0-or-later): https://github.com/qualixar/superlocalmemory. This skill only explains how to use it.

## Setup (once per computer)

1. Install the engine: `npm install -g superlocalmemory` (or `pipx install superlocalmemory`). This provides the `slm` command.
2. Connect OpenClaw: `slm connect openclaw`. This adds the `superlocalmemory` MCP server (command `slm`, argument `mcp`) under `mcp.servers` in `~/.openclaw/openclaw.json`. If that file uses JSON5 syntax, run instead: `openclaw mcp add superlocalmemory --command slm --arg mcp`.
3. Restart OpenClaw. Check the setup with `slm doctor`.

## When to recall

Before answering a question about the user's projects, preferences or earlier decisions, look it up first:
- MCP tool `recall` with a short natural-language query, or
- shell: `slm recall "what did we decide about the database"`

Use what comes back as context, and say so when an answer rests on a recalled memory.

## When to remember

Save things that will matter in a later session: a decision and its reason, a user preference, a fixed bug and its cause, a fact about the project.
- MCP tool `remember` with the content and optional `tags`, or
Read the full skill on GitHub

Details

Skill name
superlocalmemory
Path
clawhub-skill/superlocalmemory/SKILL.md
License
AGPL-3.0
Repo updated
18 November 2026

FAQ

What does the Superlocalmemory skill do?

Long-term memory for OpenClaw that stays on your computer. Recall past decisions and save new ones with SuperLocalMemory.

How do I install the Superlocalmemory skill?

Claude Code plugin: /plugin marketplace add qualixar/superlocalmemory. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Superlocalmemory popular?

It lives in qualixar/superlocalmemory, which has 278 GitHub stars and 36 forks, and is included in 1 curated skill list.

Related skills

Slm Bot Memory

278

qualixar/superlocalmemory

Cross-bot memory on a shared computer (Grok Bot, Cursor plugin, any host where several agents share one machine). Explains agent_id attribution vs. profile/scope access, how to namespace by agent_id + profile + scope, and what must never be written to memory. Read this before the first remember/recall on a new Grok-Bot-style host.

Productivity & NotesIn 1 list36

Slm Cache

278

qualixar/superlocalmemory

KV cache for repeated reads — call slm_cache_get(key) first; on a miss do the expensive operation then slm_cache_set(key, value, ttl_seconds) to store it; on a hit use the returned value directly; always fail-open (hit:false on any error, never raises); saves tokens when the same file, query result, or tool output is read more than once in a session.

OtherIn 1 list36

Slm Compress

278

qualixar/superlocalmemory

Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slm_compress(content, mode, reversible, ttl_seconds) to shrink content; if the result is lossy a ccr_id is returned so you can call slm_retrieve(ccr_id) later to recover the exact original; always fail-open (ok:false → continue with the original).

Writing & ContentIn 1 list36

Linear

230

initializ/forge

Read Linear issues, transition state, and post comments. The entry point for ticket-driven agent workflows.

Productivity & Notes17

Slm Scope

278

qualixar/superlocalmemory

Controls memory visibility across profiles — personal (private, default), shared (selected profiles), or global (all profiles on this machine). Default is always personal. Only change scope when the user explicitly asks to share a memory across workspaces. Works with both remember (write scope) and recall (read scope flags).

Productivity & NotesIn 1 list36

Multica Review Product

279

it235/multica-best-practices

需求/PRD 专属评审框架。ProductReviewer 对 multica-pm-artifact-publish 提交的 PRD 做价值/逻辑/清晰度三阶段评审,输出 PASS/FAIL/BLOCKED 与 Must Fix/Suggest/Nit,汇报 Leader;FAIL 后 PM Workflow B 复审。

Productivity & Notes33

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.