memory-lancedb

memory-lancedb is a skill for Claude Code, Codex from aaronnat23/disp8ch. It costs 0 tokens per session (219 once invoked), scanned A, original, MIT.

A memory backend that stores searchable vector representations in LanceDB, a database designed for collections of numeric search data. It supports the same memory operations as the default backend.

In plain words
What is it for?
It helps store, search, and retrieve agent memories, including automatic capture and recall, and supports moving existing embeddings through a backfill.
Why use it?
It is intended for large embedding collections when the default sqlite-vec storage becomes slower during heavy indexing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/aaronnat23/disp8ch/memory-lancedb
Any agent
npx skills add aaronnat23/disp8ch --skill memory-lancedb
Clone the repo
git clone --depth 1 https://github.com/aaronnat23/disp8ch

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for memory-lancedb

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaronnat23/disp8ch/memory-lancedb.svg)](https://agentmods.dev/skills/aaronnat23/disp8ch/memory-lancedb)
Your own site
<a href="https://agentmods.dev/skills/aaronnat23/disp8ch/memory-lancedb"><img src="https://agentmods.dev/badge/skills/aaronnat23/disp8ch/memory-lancedb.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 219 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00219
Opus 5 $0.00000 $0.00110
Sonnet 5 $0.00000 $0.00044
Haiku 4.5 $0.00000 $0.00022

Measured 6d ago against content hash 6459d95eaa7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

memory-lancedb scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

extensions/memory-lancedb/skills/memory-lancedb/SKILL.md · 13 lines

What it actually says

Memory LanceDB

LanceDB-backed vector memory for high-volume embedding and retrieval workloads.

  • LanceDB stores embeddings as Lance columnar format on disk — significantly faster for large collections (>100k vectors) than sqlite-vec.
  • Use this backend when the default sqlite-vec backend shows degraded search performance under heavy indexing load.
  • All standard memory operations (memory_search, memory_store, memory_get) work identically — the backend switch is transparent.
  • Configure dbPath in the extension settings to point to the desired LanceDB directory (defaults to data/lancedb/).
  • For auto-capture mode: the agent automatically stores conversation context chunks without explicit memory_store calls.
  • For auto-recall mode: relevant memories are automatically injected into context at session start without explicit memory_search calls.
  • When switching from sqlite-vec to LanceDB: run a memory backfill to migrate existing embeddings to the new backend.
  • Monitor embedding batch health via /api/memory?action=embedding-status to confirm the LanceDB backend is active.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 13 lines · 0 tokens per session scan A 6459d95eaa7e

Subscribe to this mod's changes

memory-lancedb is a skill published in the GitHub repository aaronnat23/disp8ch (99 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 219 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.