Skip to content

Learn

LLM wiki and AI knowledge base guides that stay current.

Wenlan turns trusted sources and durable work facts into a local, source-backed AI knowledge base with maintained LLM-wiki pages for agents and people.

Quick answer

An AI knowledge base stores and retrieves trusted sources. A maintained LLM wiki adds reusable pages, citations, review, and refresh state. Wenlan combines those layers locally for AI agents.

Learn topics

01

AI knowledge base architecture

02

Source-backed LLM wiki

03

Claude Code and MCP

04

Knowledge-base maintenance

05

Tool comparisons

06

Local-first trust

Start here

Choose the job first: build an AI knowledge base, inspect the LLM-wiki lifecycle, connect a client, or compare adjacent tools.

Popular search paths

Search demand

Concepts

16 articles

Concept

What Is AI Work Memory?

AI work memory carries sessions, decisions, lessons, project context, and wiki pages across tools and time.

Qi-Xuan Lu5 min read

Protocol

MCP Knowledge Base Server for AI Agents

Connect Claude Code, Codex, ChatGPT, Cursor, and other AI clients to a local, source-backed knowledge base through MCP.

Qi-Xuan Lu8 min read

Privacy

Local-First AI Work Memory: Keep Context on Your Machine

Local-first AI work memory keeps sensitive project knowledge, decisions, and preferences under your control while still making them useful to assistants.

Qi-Xuan Lu5 min read

Concept

Karpathy LLM Wiki: Build a Source-Backed AI Knowledge Base

The Karpathy LLM Wiki pattern turns trusted sources into maintained AI knowledge-base pages that agents can load on demand.

Qi-Xuan Lu12 min read

Architecture

Why Wenlan Uses Readable Artifacts plus a Local Store

Wenlan keeps raw captures in a daemon-owned local store and projects readable artifacts, so AI memory stays inspectable and useful.

Qi-Xuan Lu5 min read

Architecture

AI Agent Memory Types: Working, Episodic, Semantic, and Procedural

Learn what the four AI agent memory types do, where each should live, and why facts, events, current context, and procedures need different lifecycles.

Qi-Xuan Lu7 min read

Decision

AI Agent Memory: Local vs Cloud

Choose between local-first memory and hosted memory based on privacy, portability, collaboration, and operational needs.

Qi-Xuan Lu5 min read

Problem

Why AI Coding Agents Lose Context Between Sessions

Diagnose context loss after a fresh session, compaction, or tool switch, then choose resume, project instructions, handoffs, or durable memory.

Qi-Xuan Lu5 min read

Concept

Persistent Project Context for AI Agents

Keep project decisions, constraints, and handoffs available across Claude Code, Cursor, Codex, and other AI tools.

Qi-Xuan Lu5 min read

Setup

MCP Memory Server on localhost:7878: What to Check

Understand the local daemon boundary behind Wenlan's MCP memory tools and how to troubleshoot port 7878.

Qi-Xuan Lu5 min read

Capture

What to Capture in AI Work Memory

Use a simple test for deciding what belongs in Wenlan and what should stay out of memory.

Qi-Xuan Lu5 min read

Trust

Build a Source-Backed AI Knowledge Base for Agents

Build a source-backed AI knowledge base by connecting trusted sources, atomic knowledge, maintained LLM-wiki pages, citations, review, and refresh state.

Qi-Xuan Lu5 min read

Trust

AI Memory Provenance: Why Source IDs Matter

Understand why AI memory needs source trails, supersession, and review before old context steers new work.

Qi-Xuan Lu5 min read

Trust

Local Git History for AI Memory Artifacts

Why Wenlan versions readable memory artifacts in a local git repository under ~/.wenlan/.git.

Qi-Xuan Lu5 min read

Trust

How to Fix Stale AI Agent Memory

A practical diagnostic for stale, contradictory, or wrong AI agent memory: inspect the source, preserve corrections, and delete only when necessary.

Qi-Xuan Lu5 min read

Trust

Project Scope for AI Memory in Wenlan

Understand how Wenlan scopes local AI work memory with spaces, project context, and deliberate product boundaries.

Qi-Xuan Lu5 min read

Comparisons

9 articles

Comparison

AI Work Memory vs Knowledge Base: What’s the Difference?

A knowledge base maintains what is currently known. AI work memory preserves the decisions, lessons, corrections, and handoffs that agents need while working.

Qi-Xuan Lu6 min read

Comparison

Wenlan vs Basic Memory: Source-Backed AI Work vs Shared Markdown Knowledge

Compare Wenlan and Basic Memory across Markdown, MCP, local-first control, workflow fit, and how each product helps AI tools use durable context.

Qi-Xuan Lu8 min read

Comparison

Wenlan vs claude-mem: Explicit vs Automatic Agent Memory

Compare Wenlan and claude-mem for automatic session capture, explicit source-backed memory, progressive retrieval, cross-agent support, and local control.

Qi-Xuan Lu7 min read

Comparison

Wenlan vs SuperLocalMemory v3.8.3: Local AI Memory Compared

Compare Wenlan and SuperLocalMemory v3.8.3 across local agent memory, temporal retrieval, auditability, team controls, MCP workflows, and source-backed pages.

Qi-Xuan Lu7 min read

Comparison

Wenlan vs mcp-memory-service: Local AI Work Memory or Agent Pipeline Backend?

Compare Wenlan with mcp-memory-service across user workflow, transports, storage control, and agent-pipeline scope.

Qi-Xuan Lu5 min read

Comparison

Wenlan vs ChatGPT Memory: Built-In Personalization or Local AI Work Memory?

Compare built-in assistant memory with Wenlan's local, inspectable, cross-tool work-memory layer.

Qi-Xuan Lu5 min read

Comparison

Obsidian + Claude Code: Vault Access, MCP, and a Durable AI Knowledge Base

Use Obsidian with Claude Code through direct vault files, live editor context, or MCP—and add a source-backed knowledge lifecycle only when access is not enough.

Qi-Xuan Lu5 min read

Comparison

Wenlan vs Notion AI: Local AI Work Memory or Team Workspace AI?

Compare Wenlan's local AI work memory with Notion AI's workspace, agents, meetings, and enterprise search features.

Qi-Xuan Lu5 min read

Comparison

Wenlan vs Mem0: Personal AI Work Memory or App Memory Infrastructure?

Compare Wenlan's local AI work-memory loop with Mem0's memory infrastructure for AI agents and applications.

Qi-Xuan Lu5 min read

Workflows

21 articles

Developer workflow

Claude Code Memory: CLAUDE.md, /memory, and MCP Context

Understand CLAUDE.md, Claude Code auto memory, /memory, and when to add Wenlan's local MCP memory for shared project context.

Qi-Xuan Lu7 min read

Workflow

Wenlan for Claude Code Memory: The Daily /brief and /handoff Loop

Use Wenlan inside Claude Code with /setup, /brief, /capture, /recall, /handoff, and /distill so coding context carries across sessions.

Qi-Xuan Lu6 min read

Workflow

The AI Agent Handoff Loop: How Work Carries Across Sessions

A practical model for carrying decisions, lessons, gotchas, and next steps from one AI work session into the next.

Qi-Xuan Lu5 min read

Setup

Where Wenlan Stores Claude Code Memory

Find the local files Wenlan writes when Claude Code captures memories, handoffs, and distilled pages.

Qi-Xuan Lu5 min read

Setup

How to Add Memory to Claude Code

Install Wenlan's Claude Code plugin, run /setup, and verify a local memory round trip.

Qi-Xuan Lu5 min read

Claude Code

Claude Code /memory vs Wenlan: Native Memory or Shared Local Context?

Use Claude Code /memory for native project memory inspection, and use Wenlan when context needs provenance, handoff, and cross-tool MCP access.

Qi-Xuan Lu5 min read

Setup

How to Give Codex Persistent Memory

Connect Codex to Wenlan through MCP so sessions can recall local project context instead of starting from scratch.

Qi-Xuan Lu5 min read

Setup

Cursor Memory MCP: How to Add Local AI Work Memory

Wire Cursor to Wenlan's local MCP memory server so coding sessions can capture and recall project context.

Qi-Xuan Lu5 min read

Setup

Claude Desktop MCP Memory Setup with Wenlan

Connect Claude Desktop to Wenlan's local memory daemon through MCP and verify the first memory loop.

Qi-Xuan Lu5 min read

Workflow

Wenlan Workflow for Codex

Use Wenlan with Codex for session context, durable captures, recall, and cross-tool handoff.

Qi-Xuan Lu5 min read

Workflow

Wenlan Workflow for Cursor

Use Wenlan from Cursor to keep project memory available across edits, branches, and future AI sessions.

Qi-Xuan Lu5 min read

Workflow

Wenlan Workflow for Claude Desktop

Use Claude Desktop with Wenlan MCP memory for planning, research, and handoff context that later coding agents can reuse.

Qi-Xuan Lu5 min read

Workflow

Wenlan Workflow for Gemini CLI

Connect Gemini CLI as an MCP client and use Wenlan for local capture, recall, and handoff-style notes.

Qi-Xuan Lu5 min read

Workflow

Wenlan Workflow for VS Code MCP Clients

Use Wenlan as a local memory server from VS Code surfaces that support MCP.

Qi-Xuan Lu5 min read

Workflow

Claude Code Session Handoff with Wenlan

Close Claude Code sessions with enough context for the next agent to resume without replaying the chat.

Qi-Xuan Lu5 min read

Workflow

How to Share Memory Between Cursor and Claude Code

Connect Cursor and Claude Code to one local Wenlan daemon so both tools can recall the same source-backed decisions and handoffs.

Qi-Xuan Lu5 min read

Workflow

Shared Memory Between Codex and Claude Code

Use Wenlan to carry implementation context between Codex sessions and Claude Code plugin workflows.

Qi-Xuan Lu5 min read

Workflow

A Multi-Agent Memory Workflow That Stays Local

Coordinate multiple AI clients through one local, source-backed Wenlan system without turning project context into a cloud black box.

Qi-Xuan Lu5 min read

Workflow

AI Agent Project Status Handoff

Keep project status usable for the next AI session without bloating memory with transient todos.

Qi-Xuan Lu5 min read

Workflow

How to Build a Local AI Knowledge Base from Markdown, PDFs, and Obsidian

Use supported document sources, repeatable sync, source-backed pages, and verification to build a local AI knowledge base for coding agents.

Qi-Xuan Lu5 min read

Selection guide

How to Choose an AI Knowledge Base Tool: 8 Tests That Matter

Choose an AI knowledge base by testing sources, freshness, review, ownership, privacy, agent access, input limits, and real answer quality.

Qi-Xuan Lu5 min read

Ready to try the local memory loop?

Make AI work carry forward.

Install Wenlan, connect your AI tools, and verify the first memory loop locally.