llm-wiki-agent
An intelligent agent for automatically building and maintaining a personal knowledge base, supporting multiple document formats.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 2.9k
- Source
- GitHub
- Added
- 2026-06-17
- Last verified
- 2026-06-17
Overview
LLM Wiki Agent is an intelligent agent that automatically builds and maintains a personal knowledge base. Users simply place source files into a designated directory, and the agent will read, extract knowledge, and generate a persistent, interconnected wiki. It supports various document formats and does not require an API key. Suitable for researchers, students, and personal knowledge management. Users can easily import documents, perform queries, and build knowledge graphs using natural language commands or specific instructions.
Key features
- ▪Automatic reading and knowledge extraction
- ▪Generation of persistent, interconnected wiki
- ▪Support for multiple document formats
- ▪No API key required
Use cases
Pros
- +Automated knowledge extraction
- +Multi-format support
- +No API key required
- +Continuously updated knowledge base
Limitations / notes
- -Requires internet connection
- -Higher learning curve
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
Is it free?
Yes, the project is open-source and free.
Does it support Chinese?
The project documentation is primarily in English, but it supports processing documents in multiple languages.
Do I need to use a proxy or scientific internet access?
Not required, but internet access is needed to use related services.
Can it be used commercially?
Yes, the project is licensed under the MIT License.
Similar agents
Perplexity
FeaturedAI Search and Research Assistant
秘塔 AI 搜索
FeaturedAd-free Chinese AI search/research
Felo
Multilingual AI Search
Kimi 探索版
Deep search/research by Moonshot
纳米 AI 搜索
Multi-Agent AI Search by 360
OpenAI Deep Research
Multi-step Online Deep Research Agent
Something wrong? Let us know on the About page and we'll fix it.