Oshayr

Oshayr / LLM-Wiki

Public

Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.

ai-tools autonomous-agent claude-code claude-code-plugin fastapi
20
0
100% credibility
Found Apr 13, 2026 at 20 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

LLM-Wiki is a plugin that turns your AI conversations into a self-maintaining, searchable knowledge base with a Wikipedia-style web interface and automatic research.

How It Works

1
🔍 Discover the wiki helper

You hear about a smart notebook that saves your research and ideas automatically while chatting with your AI assistant.

2
📥 Add it easily

Tell your AI to install the wiki tool, and it sets everything up in seconds without any hassle.

3
💭 Ask anything

Type a question like 'What is machine learning?', and it pulls from your notes or finds answers online, saving them neatly.

4
🌐 Browse like Wikipedia

Open a beautiful web page to read, search, and explore your growing collection of knowledge.

5
✏️ Grow your notes

Click red links to auto-fill missing info, edit pages, or chat for quick help right in the browser.

📚 Smarter every day

Your personal wiki remembers everything, connects ideas, and keeps getting better as you use it.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 20 to 20 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is LLM-Wiki?

LLM-Wiki is a Python plugin for Claude Code that builds an autonomous knowledge base from your research, ideas, and decisions, turning them into an interlinked wiki with semantic search and a Wikipedia-style web UI. It auto-researches missing topics via research-on-miss, using commands like /wiki-read for queries, /wiki-write for ingestion, and /wiki-serve for localhost browsing. This creates a compounding llm wiki that grows smarter as you code, handling everything from daily notes to knowledge graphs.

Why is it gaining traction?

Its killer hook is autonomous knowledge acquisition—agents auto-fill gaps, maintain freshness with 9 staleness tiers, and offer live research on red links, plus Cytoscape graphs and FSRS spaced repetition. Unlike basic note apps, it integrates git tracking, RAG chat, and MCP tools for seamless Claude flows, echoing Karpathy's llm wiki pattern but with full autonomy for coders exploring autonomous knowledge graphs.

Who should use this?

Claude Code power users in AI research, like devs building github autonomous agents, autonomous coder github tools, or autonomous driving knowledge graphs. Ideal for teams tracking project decisions, research scans, or llm wiki english setups where knowledge compounds across sessions.

Verdict

Promising for Claude-heavy workflows despite 20 stars and 1.0% credibility score—strong docs and features, but early-stage with no tests or broad polish. Prototype it for autonomous knowledge systems; skip if you need battle-tested stability.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.