lians

A local memory system for AI agents that records when facts became true and when they were stored or changed. It supports recalling past states, replacing outdated facts in a defined way, erasing records, and keeping a tamper-evident history.

In plain words
What is it for?
Use it to store and recall durable agent knowledge, inspect memory at a past point in time, connect local tools through MCP, prove erasure, and review the integrity of the memory history.
Why use it?
It gives an agent memory that can be checked as of an earlier date instead of only showing its current state. This helps track changes, investigate history, and confirm what was removed.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add Lians-ai/Lians
agentmods
npx agentmods add plugins/lians-ai/lians/lians-plugin
Clone the repo
git clone --depth 1 https://github.com/Lians-ai/Lians

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

lians 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 2d 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.

integrations/lians-plugin/.claude-plugin/plugin.json · 26 lines

What it actually says

{
  "name": "lians",
  "description": "Bitemporal memory for Claude Code with deterministic supersession, point-in-time recall, local MCP, erasure proofs, and tamper-evident history.",
  "version": "0.5.0",
  "author": {
    "name": "Lians",
    "email": "[email protected]",
    "url": "https://github.com/Lians-ai/Lians"
  },
  "homepage": "https://github.com/Lians-ai/Lians",
  "repository": "https://github.com/Lians-ai/Lians",
  "license": "Apache-2.0",
  "keywords": [
    "memory",
    "agent-memory",
    "compliance",
    "bitemporal",
    "audit",
    "finance",
    "healthcare",
    "legal",
    "gdpr",
    "point-in-time"
  ]
}
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. 2d ago First seen · 26 lines scan A 1dd0058f20cb

Subscribe to this mod's changes

lians is a plugin published in the GitHub repository Lians-ai/Lians (10 stars, last pushed 9d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.