Claude Code mod

neo4j-memory

Persistent memory for Claude Code in a local SQLite file (node:sqlite; no server, no container). Injects standing facts and a subsystem map at session start, captures new facts at compaction and session end, and exposes search tools. A machine's Neo4j graph moves across by itself on first start.

1 starsMemory & instructions modsValidates on Claude Code 2.1.316 Source

Install

From source
git clone https://github.com/troglodyte/claude-sqlite-mem.git
claude --plugin-dir ./claude-sqlite-mem/.

The repo has no marketplace file, so load the plugin folder directly with --plugin-dir.

What it can access

Reach
L2Writes or runs: runs processes, reads mod state, draws
Draws in
Pane
Hooks
session.startcommand.runturn.completeui.render

From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.

How Claude Code mods work

  • A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
  • It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
  • Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
  • Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Claude Code docs

Details

Folder
.
Author
Michael Harris
Last updated
22 October 2026

FAQ

What is neo4j-memory?

Persistent memory for Claude Code in a local SQLite file (node:sqlite; no server, no container). Injects standing facts and a subsystem map at session start, captures new facts at compaction and session end, and exposes search tools. A machine's Neo4j graph moves across by itself on first start. It is a mod for Claude Code, from troglodyte/claude-sqlite-mem on GitHub.

What can the neo4j-memory mod access?

Its widest reach is "writes or runs" (runs processes, reads mod state, draws). It draws in Pane. Like any mod, it runs with your permissions.

How do I install neo4j-memory?

Clone troglodyte/claude-sqlite-mem and start Claude Code with --plugin-dir pointing at the mod's folder (.).

Is neo4j-memory popular?

troglodyte/claude-sqlite-mem has 1 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 22 October 2026.

More memory & instructions mods

model-hint

1

hashswingingslasher/model-hint

Suggests haiku, sonnet or opus for the task you are typing, live, in a band above the prompt. Instant word rules, then a small model reads the draft when you pause.

Memory & instructions mods/plugin install

segmem

1

mahuebel/segmem

Segmented, scoped memory for agents: one file, SQLite, no daemon. Wake at session start, recall on every prompt, staleness nag at stop.

Memory & instructions mods/plugin install

lumberroom-memory

1

lumberroom/lumberroom-claude-code

lumberroom as Claude Code's memory: the digest in the system prompt, a periodic search-and-write reminder, optional per-prompt recall, built-in memory off.

Memory & instructions mods/plugin install

session-handoff

1

m-tababi/session-handoff

Writes a structured session handoff on demand to ~/.claude/handoffs/<project>/ (never into the project), resumes from the newest one, restarts into a fresh conversation with the handoff (pill or /handoff fresh) and hints once when the context fills up.

Memory & instructions mods/plugin install

handoff

1

zaripovfarrukh/claude-code-mods

Hands a long session over to a fresh one before context runs out: watches the context fill, offers to write HANDOFF.md from the session's own transcript, and loads it into the next session.

Memory & instructions mods/plugin install

snagon-dev-mods

1

phantanphatdgteam-gif/snagon-dev-mods

A coding-agent harness for Claude Code as a mod that needs only Claude Code: /snagon-setup writes your project instructions without repeating the harness, a per-project memory (SQLite full-text search over JSONL, kept out of git), a fact-forcing safety gate with git hook-bypass and secret checks, session journal reminders, end-of-session handoff, cost and context notices, a flow that takes TypeScript and Python features from plan to release under the owner's approvals (tickets, tests first, a sandboxed judge, review, verify, ship), plus 64 skills, 66 agents and 43 commands.

Memory & instructions mods/plugin install

Browse the most popular Claude Code mods, all memory & instructions mods, or the skills and MCP server directories.