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.
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
Compare Wenlan with your current tools
Compare AI + files, LLM Wiki, Obsidian, Notion and NotebookLM, with sources and setup details.
Build a local AI knowledge base
Turn Markdown, text files, text PDFs, or an Obsidian vault into a source-backed knowledge workflow.
AI knowledge base for agents
Build maintained pages with sources, review, refresh state, and a verifiable local workflow.
Claude Code memory
See what native CLAUDE.md and auto memory cover, then decide when shared local context helps.
Codex memory
See how Codex memories and AGENTS.md work, then share project context with Claude Code.
Codex and Claude Code shared memory
Give Codex and Claude Code one local, source-backed memory both clients can recall.
Basic Memory comparison
Compare Wenlan and Basic Memory on provenance, local retrieval, shared clients, and wiki pages.
MCP memory server
Connect Claude Code, Codex, Cursor, ChatGPT, and other MCP clients to Wenlan.
Karpathy LLM wiki for AI agents
Turn trusted sources and durable work context into a maintained AI knowledge base with inspectable support.
Cursor memory MCP
Wire Cursor to Wenlan's local MCP memory server and verify recall.
AI work memory vs knowledge base
Separate reusable decisions and handoffs from the source-backed pages they maintain.
Connect Claude Code to Obsidian
Connect your vault, find the latest decision in two practice notes, and check the original sources.
Local AI memory
Keep project context local, inspectable, and under your control.
How Wenlan works
See how the daemon, MCP connector, local index, and source-backed pages fit together.
Concepts
8 articles
Concept
What Is AI Work Memory?
AI work memory carries sessions, decisions, lessons, project context, and wiki pages across tools and time.
Protocol
MCP Memory Server: How It Works, Setup for Claude Code and Cursor, and Which One to Use
What an MCP memory server is, how to set up the official memory server in Claude Code, Codex, Cursor, and VS Code, where it stores data, and how the popular options compare.
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.
Guide
Karpathy's LLM Wiki: What It Is and How to Build One
Karpathy's LLM Wiki explained: add documents, build linked pages, ask questions with sources, and check what changes when evidence is updated.
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.
Decision
AI Agent Memory: Local vs Cloud
Choose between local-first memory and hosted memory based on privacy, portability, collaboration, and operational needs.
Problem
Why AI Coding Agents Lose Context Between Sessions
Resume the right session, check unfinished work, and give the next agent a clear starting point.
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.
AI tools and shared memory
7 articles
Developer guide
Claude Code Memory: How It Works, Where It's Stored, and How to Extend It
How Claude Code memory works: CLAUDE.md vs auto memory, where MEMORY.md lives, how to view, clear, or turn it off, why it forgets your last session, and when a plugin helps.
Developer workflow
Codex Memory: MEMORY.md, Setup, and AGENTS.md
Find Codex's MEMORY.md, understand how it loads, and enable native memories. Keep required rules in AGENTS.md; use shared MCP memory when other AI tools need the same project knowledge.
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.
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.
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.
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.
Workflow
How to Share Memory Between Codex and Claude Code
Connect both tools to one Wenlan Space, save a decision in Claude Code, and recall it in a fresh Codex session. Inspect our recorded input, receipt, and matching result.
Build a knowledge base
16 articles
Developer workflow
Obsidian + Claude Code: Connect Your Vault and Check Answers
Connect Claude Code to Obsidian, find notes for a project without knowing their filenames, and check the latest decision against its sources. Includes setup, a tested search prompt, and example results; MCP and plugins are optional.
Coding agent knowledge
How to Give Codex a Source-Backed Project Knowledge Base
Keep repository rules, source-of-truth documents, and maintained project knowledge separate so Codex can retrieve evidence without loading everything.
Research workflow
Build a Research Knowledge Base from Papers and PDFs
Turn a bounded paper set into inspectable research notes that preserve claims, methods, limitations, contradictions, citations, and source updates.
Selection guide
AI Second Brain: Choose an App or Build Your Own?
See how notes become useful work, then compare Claude Code or Codex, Obsidian with optional AI, and Wenlan’s maintained Wiki.
Migration guide
Migrate an Obsidian Vault to a Source-Backed LLM Wiki
Register an Obsidian vault as a Wenlan source that Wenlan follows in the background and never edits without your OK, and distill the most-reused notes into citation-backed wiki pages that AI agents can query.
Setup guide
Set Up a Knowledge Base Your Coding Agents Can Query
Install the Wenlan runtime, connect Claude Code, Codex, and Cursor, add one project source set, and prove the capture, distill, cite, and refresh loop before expanding.
Consulting workflow
How to Build a Client Project Knowledge Base for Consulting
Keep one consulting engagement's sources, research, decisions, deliverables, and handoff context in a traceable client-project knowledge base.
Investment research workflow
How to Build an Investment Research Knowledge Base
Turn annual reports, filings, earnings-call notes, and research questions into a source-backed company dossier that stays reviewable as evidence changes.
SRE knowledge workflow
How to Build an SRE Incident Knowledge Base
Turn runbooks, postmortems, and approved incident notes into current, source-backed operational knowledge for on-call engineers.
Competitive intelligence workflow
How to Build a Source-Backed Competitive Intelligence Knowledge Base
Keep competitor research current with a bounded source register, dated evidence, explicit uncertainty, and reviewable knowledge-base Pages.
Supplier review workflow
How to Build an ICT Supplier Due Diligence Evidence Pack
Organize approved software-supplier documents into a source-backed evidence pack with provenance, scope, gaps, owners, and review dates.
Support answer workflow
How to Build a Customer Support Answer Knowledge Base
Keep customer-support answers reviewable after product or policy changes with approved sources, explicit scope, prohibited promises, owners, and review dates.
Course wiki workflow
How to Build a Course Wiki from Lecture Notes and PDFs
Turn one course's readable lecture slides, notes, and PDFs into a maintained wiki with exact sources, prerequisite links, revisions, and review state.
Data dictionary workflow
How to Build a Business Metric Definition Knowledge Base
Turn approved KPI specifications into a source-backed data dictionary with formula text, grain, exclusions, owners, revisions, and review state.
Workflow
Build a Personal AI Knowledge Base from Your Documents
Ask questions across your notes and documents, with sources you can check. No terminal needed.
Product research workflow
Build a Product Research Knowledge Base Before Writing a PRD
Turn approved research notes, support and sales signals, and prior decisions into a source-backed evidence base for a defensible PRD.
Maintain and verify
6 articles
Shared knowledge maintenance
How to Prevent Multi-Agent Knowledge Conflicts and Stale Conclusions
Prevent AI agents from overwriting shared knowledge, promoting unsupported claims, or reusing conclusions after their sources change.
Ingestion troubleshooting
PDF Failed to Ingest into Your AI Knowledge Base? Diagnose It First
Diagnose empty, skipped, malformed, oversized, or image-only PDFs before trusting an AI knowledge base or RAG answer.
Retrieval policy
When Should an AI Agent Query a Knowledge Base?
Use a query-or-skip policy so AI agents retrieve authoritative knowledge when needed without repeatedly loading irrelevant documents into context.
Trust check
How to Verify AI Knowledge Base Citations and Unsupported Claims
Audit a RAG or AI knowledge-base answer claim by claim to find wrong pages, mismatched chunks, stale sources, and unsupported conclusions.
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.
Retrieval regression
How to Regression-Test AI Knowledge Base Retrieval After Changes
Use a versioned golden query set to find RAG retrieval regressions after corpus, embedding, chunking, hybrid search, or reranker changes.
Tool comparisons
8 articles
Comparison
AI Memory vs Knowledge Base: What’s the Difference?
AI memory carries earlier decisions and preferences into the next task. A knowledge base provides reusable references. Here is how to choose, with a real Claude-to-Codex example.
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.
Comparison
Wenlan vs claude-mem: Which AI Memory Tool Should You Use?
claude-mem automatically captures and compresses your agent sessions; Wenlan keeps explicit, source-backed memory you review and maintain as readable pages. Compare capture, retrieval, cross-agent support, and control.
Comparison
Wenlan vs SuperLocalMemory v3.8.3: Which Local AI Memory Fits Your Work?
A historical comparison of SuperLocalMemory v3.8.3 and Wenlan v0.14.1, pinned to July 24, 2026. SuperLocalMemory v4.2.10 was released October 17; current features and benchmark standing have not been retested here.
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.
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.
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.
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.
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.