install-memu
VerifiedInstall or uninstall memU for whatever agent you are — identify your host, print its packaged guide, and follow it to wire (or unwire) both seams (record and inject). Use when the user asks to install, set up, integrate, remove, or uninstall memU.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.8 KB |
| assets/banner.png | binary | 258.1 KB |
| assets/benchmark.png | binary | 76.8 KB |
| assets/memUbot.png | binary | 285.0 KB |
| assets/memorize.png | binary | 889.1 KB |
| assets/partners/Clawdchat.png | binary | 470.5 KB |
| assets/partners/LazyLLM.png | binary | 247.7 KB |
| assets/partners/buddie.png | binary | 13.1 KB |
| assets/partners/bytebase.png | binary | 22.6 KB |
| assets/partners/jazz.png | binary | 30.9 KB |
| assets/partners/openagents.png | binary | 15.3 KB |
| assets/partners/xroute.png | binary | 44.1 KB |
| assets/qrcode.png | binary | 160.7 KB |
| assets/retrieve.png | binary | 840.0 KB |
| assets/skill-extraction.png | binary | 1.3 MB |
| assets/star.gif | binary | 2.9 MB |
| assets/structure-v2.png | binary | 1.3 MB |
| assets/structure.png | binary | 1.6 MB |
| assets/usecase/ai_companion-0000.jpg | binary | 19.0 KB |
| assets/usecase/ai_creation-0000.jpg | binary | 18.5 KB |
| assets/usecase/ai_edu-0000.jpg | binary | 22.1 KB |
| assets/usecase/ai_ip-0000.png | binary | 556.1 KB |
| assets/usecase/ai_robot-0000.jpg | binary | 14.4 KB |
| assets/usecase/ai_role_play-0000.jpg | binary | 25.0 KB |
| assets/usecase/ai_therapy-0000.jpg | binary | 15.5 KB |
| scripts/db.py | script | 3.1 KB |
scripts/db.py
View on GitHub#!/usr/bin/env python
"""Programmatic Alembic entry point for the Postgres backend.
The migration environment is parameterized by a user *scope model* (see
``memu.database.postgres.schema.get_metadata``). The bare ``alembic`` CLI cannot
pass that in, so this wrapper builds the config via
``memu.database.postgres.migration.make_alembic_config`` and drives Alembic's
command API directly.
The default scope model is ``None`` (the base schema with no scope columns),
which is the schema committed under ``migrations/versions``.
Usage:
python scripts/db.py revision -m "add foo" # autogenerate a revision
python scripts/db.py upgrade [head] # apply migrations
python scripts/db.py downgrade -1 # revert one revision
python scripts/db.py current # show applied revision
python scripts/db.py history # show revision history
DSN resolution: --dsn, else $MEMU_DB_DSN, else a localhost default.
"""
from __future__ import annotations
import argparse
import os
import sys
from alembic import command
from memu.database.postgres.migration import make_alembic_config
DEFAULT_DSN = "postgresql+psycopg://postgres:postgres@localhost:5432/memu"
def _config(dsn: str):
# scope_model=None -> base schema (matches committed baseline revision).
return make_alembic_config(dsn=dsn, scope_model=None)
def main(argv: list[str] | None = None) -> int:
parser = argparse.ArgumentParser(description="MemU Postgres migrations")
parser.add_argument(
"--dsn",
default=os.environ.get("MEMU_DB_DSN", DEFAULT_DSN),
help="SQLAlchemy DSN (default: $MEMU_DB_DSN or localhost memu db)",
)
sub = parser.add_subparsers(dest="cmd", required=True)
p_rev = sub.add_parser("revision", help="create a new revision")
p_rev.add_argument("-m", "--message", required=True)
p_rev.add_argument(
"--no-autogenerate",
action="store_true",
help="create an empty revision instead of diffing against the DB",
)
p_up = sub.add_parser("upgrade", help="apply migrations")
p_up.add_argument("revision", nargs="?", default="head")
p_down = sub.add_parser("downgrade", help="revert migrations")
p_down.add_argument("revision")
sub.add_parser("current", help="show current revision")
p_hist = sub.add_parser("history", help="show revision history")
p_hist.add_argument("-v", "--verbose", action="store_true")
args = parser.parse_args(argv)
cfg = _config(args.dsn)
if args.cmd == "revision":
command.revision(cfg, message=args.message, autogenerate=not args.no_autogenerate)
elif args.cmd == "upgrade":
command.upgrade(cfg, args.revision)
elif args.cmd == "downgrade":
command.downgrade(cfg, args.revision)
elif args.cmd == "current":
command.current(cfg, verbose=True)
elif args.cmd == "history":
command.history(cfg, verbose=args.verbose)
else: # pragma: no cover - argparse guards this
parser.error(f"unknown command: {args.cmd}")
return 0
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |