Linggen Memory

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; 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 shared-memory 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.

See doc/product-spec.md for the full product story and doc/tech-spec.md for the implementation contract.

Quick look

# Add a fact
ling-mem add "prefers concise replies, no hedging" \
  --type preference --from user

# Semantic search
ling-mem search "how do I format logs in dev" \
  --context code/linggen --limit 5

# Browse by filter
ling-mem list --type preference --since 2026-01-01 --format text

# Forget a finished project
ling-mem forget --context trip-japan-2026 --yes

Default output is NDJSON on stdout — any model / script / shell can parse it. Pass --format text for human-readable lines.

The daemon (ling-mem start) also serves a built-in Data Browser at http://127.0.0.1:9888 for hands-on filter / edit / batch-delete.

Install

The ling-mem binary ships as part of the shared-memory skill (in the linggen/skills repo at shared-memory/). Installing the skill is the recommended path — it fetches the prebuilt binary, wires up the SKILL.md, and seeds the core memory files.

Best experience: Linggen agent, which exposes typed Memory_query / Memory_write tools and a built-in dashboard. The skill also works with any other agent that can shell out (Claude Code, Codex, OpenClaw, plain scripts) — they just call the ling-mem CLI directly.

Install from your agent's own marketplace — it manages updates and (on Claude Code / Codex) the per-turn recall hook. Pick one channel per host:

Claude Code   /plugin marketplace add linggen/linggen-memory
              /plugin install shared-memory@linggen-memory
Codex         codex plugin marketplace add linggen/linggen-memory
              codex plugin add shared-memory@linggen-memory
OpenClaw      clawhub install ling-mem
Any agent     npx skills add linggen/linggen-memory@shared-memory
Linggen       Settings → Skills → shared-memory   (in-app)

The ling-mem binary is fetched automatically on first use (pinned, SHA-256 verified) to the one cross-host location ~/.local/bin/ling-mem. To install just the binary manually:

bash <(curl -fsSL https://raw.githubusercontent.com/linggen/linggen-memory/main/plugins/shared-memory/scripts/install-bin.sh) --version '^1'

Prebuilt binaries for macOS Apple Silicon and Linux x8664 are on the releases page.

git clone https://github.com/linggen/linggen-memory
cd linggen-memory
cargo build --release
./target/release/ling-mem --help

linggen-memory/
├── Cargo.toml          # single crate
├── src/                # all Rust code (CLI, HTTP daemon, embed pipeline,
│                       #  LanceDB store)
├── static/             # Data Browser UI (baked into the binary via rust-embed,
│                       #  served at 127.0.0.1:9888 by the daemon)
├── doc/
│   ├── product-spec.md # features, user-facing behavior, scenarios
│   ├── tech-spec.md    # schema, storage, CLI contract, release process
│   └── ui-spec.md      # Data Browser UI: layout, endpoints, interactions
├── scripts/            # release.sh + Dockerfile.linux (multi-arch buildx)
├── assets/             # icon etc.
├── CHANGELOG.md        # release notes per version
├── LICENSE             # MIT
└── README.md           # you are here