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.
Install
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.
Details
- Repository
- troglodyte/claude-sqlite-mem
- Folder
.- Author
- Michael Harris
- Last updated
- 22 October 2026
- Listed in
- awesome-claude-code-mods
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
1hashswingingslasher/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.
segmem
1mahuebel/segmem
Segmented, scoped memory for agents: one file, SQLite, no daemon. Wake at session start, recall on every prompt, staleness nag at stop.
lumberroom-memory
1lumberroom/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.
session-handoff
1m-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.
handoff
1zaripovfarrukh/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.
snagon-dev-mods
1phantanphatdgteam-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.
Browse the most popular Claude Code mods, all memory & instructions mods, or the skills and MCP server directories.