AgentIndex icon
AgentIndex
wenlan logo
wenlan
★ 86
vs
deja-vu logo
deja-vu
★ 1.3k

wenlan vs deja-vu

wenlan: Wenlan is a living personal knowledge library for the AI-native age, built by your agents and grounded in its sources. It continuously evolves between sessions, distilling captures into source-cited wiki pages that feed retrieval.; deja-vu: Deja-vu is a zero-dependency, local-first binary that indexes and makes searchable the historical sessions of various AI coding agents. It acts as a universal memory layer, allowing agents to recall past solutions and context efficiently, even from before its installation.

01

TL;DR

wenlan logo
wenlanRAG / Knowledge Base · ★ 86

Capture decisions, lessons, and facts from AI agent interactions to build a persistent knowledge base.

Read wenlan full review →
deja-vu logo
deja-vuMemory & Context · ★ 1.3k

Reusing solutions from past agent conversations to avoid re-debugging or re-implementing.

Read deja-vu full review →
02

Side-by-Side Comparison

Field
wenlan logowenlan
deja-vu logodeja-vu
Category
RAG / Knowledge Base
Memory & Context
Stars
★ 86
★ 1.3k
License
Apache-2.0
MIT
Install Command
npx -y wenlan setup && ~/.wenlan/bin/wenlan install
curl -fsSL https://raw.githubusercontent.com/vshulcz/deja-vu/main/install.sh | sh
Updated
1d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Agent Memory, Personal Knowledge Management, RAG
AI Agent Memory, Session Search, Code Assistant
03

Features

wenlan logowenlan
01Trustworthy and source-cited knowledge pages, with hallucination prevention and fact deduplication.
02Self-evolving knowledge base that updates and refines between sessions without manual maintenance.
03Real Git versioning for all memories, pages, and sessions, enabling inspection, diff, and revert.
04Unified local daemon serving context to multiple MCP-compatible AI clients.
05Hybrid retrieval system leveraging vector embeddings, FTS5, and graph context for relevant recall.
deja-vu logodeja-vu
01Fast, Retroactive Session Search
02Automatic AI Agent Memory Recall
03Cross-Machine Memory Synchronization
04Seamless Agent Context Handoff
05Automated Sensitive Data Redaction
04

Use Cases

wenlan logowenlan
↳Capture decisions, lessons, and facts from AI agent interactions to build a persistent knowledge base.
↳Maintain continuous, topic-relevant context across multiple AI agent sessions and projects.
↳Distill raw agent captures and existing documents into trustworthy, source-cited wiki pages.
↳Integrate a shared memory and context layer across various AI development environments like Claude Code, Cursor, and VS Code.
deja-vu logodeja-vu
↳Reusing solutions from past agent conversations to avoid re-debugging or re-implementing.
↳Debugging complex issues by accessing comprehensive past debugging sessions and design decisions.
↳Maintaining persistent context across different AI agents and development machines.
↳Sharing sanitized session digests with colleagues for onboarding or knowledge transfer.
↳Understanding file change history and decision-making via session blame.
FAQ

FAQ

What is the difference between wenlan and deja-vu?
Both wenlan and deja-vu are in the RAG / Knowledge Base category. wenlan has 86 stars, while deja-vu has 1.3k stars.
Which is better, wenlan or deja-vu?
The best choice depends on your use case. Choose wenlan if Capture decisions, lessons, and facts from AI agent interactions to build a persistent knowledge base., and deja-vu if Reusing solutions from past agent conversations to avoid re-debugging or re-implementing..
Is wenlan free or open source?
Yes, wenlan is open source on GitHub (Apache-2.0).
Is deja-vu free or open source?
Yes, deja-vu is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to wenlan →Alternatives to deja-vu →wenlan details →deja-vu details →