linggen

Linggen Memory — AI skill for Claude Code

AI community

Local-first semantic memory for AI assistants — one store your preferences, decisions and gotchas follow you into, across Claude Code, Codex, Cursor and Zed.

How to install Linggen Memory

This entry records only its repository, not the path inside it, so there is no exact command to give. Open linggen/linggen-memory and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Linggen Memory does

Local-first semantic memory for AI assistants — one store your preferences, decisions and gotchas follow you into, across Claude Code, Codex, Cursor and Zed.

Alternatives in AI

Token Monitor — Local-first desktop widget for tracking token usage, costs, and limits across 32+ AI coding tools—including Cl 1.8k ★
OpenContext — A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC 1.1k ★
Ataru — High-performance AI memory retrieval for local agent history — a Rust search core (SDK / API / JSON CLI) plus 351 ★

README

linggen-memory

**A semantic memory store for AI assistants.**

`ling-mem` is a single-binary CLI + optional web UI that remembers useful facts about you and your work across every session, every tool, and every project. LanceDB-backed, local-first, markdown-native where it counts.

Built as the default memory skill for [Linggen](https://github.com/linggen/linggen); works equally well invoked from Claude Code or any tool that can shell out.

🚀 **Status: v1.0.0 — stable** (contract frozen: store schema + CLI/HTTP/MCP API). Prebuilt binaries for macOS Apple Silicon and Linux x86_64. The pre-refactor code-indexing tool is preserved at the `v0-legacy` git tag.

What it does

Remembers across sessions. Facts about who you are, how you prefer to work, what you've tried, what worked, what didn't.
Semantic retrieval. Everything stored gets embedded (1024-dim via Qwen3-Embedding-0.6B, multilingual). Find "berth calibration" by asking about "dock alignment."
Typed facts. Four default categories — fact / preference / decision / learned — plus tried / fixed / built for trajectory-level patterns.
Forgetting is first-class. delete by id, forget by filter — refuses empty filters as a guardrail.
Self-updating. ling-mem upgrade --check reports the latest release; ling-mem start, restart, and status all embed the same cached probe in their JSON so the agent can prompt the user when a new version ships without making extra network calls. upgrade --yes swaps the binary atomically and restarts the daemon. (self-update still works as an alias.)
Three ways to use it:
- As the linggen skill on Linggen — web app UI + Memory_* tool dispatch in the agent.
- As the shared-memory skill on Claude Code / Codex / OpenClaw — SKILL.md body, model calls the CLI via Bash, recall hook injects context every turn.
- Standalone — any script or tool can shell out to ling-mem.