A project connection to a persistent knowledge base stores team notes and project information in an LLM Wiki. The memex command-line tool can search, retrieve, capture, and organize that information.

Use it to search project notes, inject relevant context into a task, capture URLs or files, and maintain a shared technical knowledge base.

It gives coding agents access to decisions and background that may not be present in the current files. This can reduce repeated explanations and help keep work aligned with team knowledge.

memex — Cursor rule for Cursor by zelixag/ai-memex-cli

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.

Clone the repo

git clone --depth 1 https://github.com/zelixag/ai-memex-cli

Made for: Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/zelixag/ai-memex-cli/memex/github.svg)](https://agentmods.dev/rules/zelixag/ai-memex-cli/memex)

Your own site

<a href="https://agentmods.dev/rules/zelixag/ai-memex-cli/memex"><img src="https://agentmods.dev/badge/rules/zelixag/ai-memex-cli/memex/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/rules/zelixag/ai-memex-cli/memex"><img src="https://agentmods.dev/badge/rules/zelixag/ai-memex-cli/memex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 454 This file is loaded in full into every session.

When invoked 454 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00454	$0.00454
Opus 5.5	$0.00182	$0.00182
Sonnet 5.5	$0.00091	$0.00091
Haiku 4.5	$0.00045	$0.00045

Measured 1mo ago against content hash ba670ce5d383, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memex 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 1mo 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.

.cursor/rules/memex.mdc · 36 lines

What it actually says

🧠 Memex Knowledge Base

This project is connected to a persistent knowledge base (LLM Wiki) managed by the memex CLI.

Vault: C:/Users/Administrator/.llmwiki
Pages: 25 (team: 25)
Updated: 2026-04-25
Agent: cursor

Index digest

team — 25 pages

[[agent-native-iteration-plan-2026-04-24]] — ai-memex-cli 从 CLI-first 转向 agent-native wiki 工作流的迭代计划文档
[[agent-first-memex-workflow]] — agent skill 是主界面，CLI 是工具箱的产品与架构原则
[[agent-native-architecture]] — ai-memex-cli 三层架构设计：Agent Interface、Workflow Protocol、CLI Toolbox
[[cli-toolbox-boundary]] — CLI 不负责语义写作、不调 LLM API、只做机械原语的架构边界定义
[[multi-agent-installation]] — agent profiles、slash prompts、skills、context files、user/project scope
…20 more (run memex status --scene team)

How to use memex from this session

memex search "<topic>" — keyword + full-text search across the wiki
memex inject --task "<current goal>" — pull the most relevant pages for your task
memex fetch <url|query> — fetch web docs / search results into raw/
memex distill / memex ingest — convert sessions/raw into structured wiki
memex watch — auto ingest → lint → ingest loop when raw/ changes
memex --help — full command list

💡 Before answering domain questions or starting non-trivial work, consult memex inject --task "<what you are trying to do>" to load relevant wiki pages.

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.

1mo ago First seen · 36 lines · 454 tokens per session scan A ba670ce5d383

Subscribe to this mod's changes

memex is a cursor rule published in the GitHub repository zelixag/ai-memex-cli (9 stars, last pushed 5mo ago), licensed MIT. It adds 454 tokens to every session, about $0.0018 per session on Opus 5.5. 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.

Claude Code Memory and context agent cli karpathy knowledge-base knowledge-compilation

memex

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

🧠 Memex Knowledge Base

Index digest

How to use memex from this session

What this file has done since we first saw it

Other cursor rules, from other repositories

unforgit-memory

digital-brain

intelligence-router

read-xlsx

ponytail

angular-20