llm-wiki-kit
Active·★ 61·MIT·Updated 2026-04-08
llm-wiki-kit gives your AI agent a persistent, structured memory that compounds over time. Drop PDFs, URLs, YouTube videos — your agent builds a wiki, connects the dots, and remembers everything across sessions. It works with Claude, Codex, Cursor, Windsurf, and any MCP-compatible agent.
#ai-agent#knowledge-base#llm#llm-tools#mcp#mcp-server#mcp-servers
01
Features
01Multi-format ingest (PDFs, URLs, YouTube, markdown)
02Auto cross-referencing with wiki links
03Persistent memory across sessions
04Full-text search via SQLite FTS5
05Health checks (broken links, orphan pages)
02
Compatibility
Claude
Claude Desktop
Verified via docs
Codex
OpenAI Codex
Verified via docs
Cursor
Cursor
Verified via docs
Windsurf
Windsurf
Verified via docs
03
Quick start
1
$ pip install "llm-wiki-kit[all] @ git+https://github.com/iamsashank09/llm-wiki-kit.git"
04
Use cases
↳Research: feed papers and ask synthesis questions across sources
↳Technical onboarding: ingest codebase docs for architecture queries
↳Learning: build a personalized wiki from tutorials and blog posts
05
Alternatives
ogham-mcp★ 116
Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode
hmem★ 24
Humanlike persistent memory for AI agents — MCP server with 5-level lazy-loaded SQLite memory. Works with Claude Code, Gemini CLI, Cursor, Windsurf, OpenCode.
its-over-9k★ 0
Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.
Matryoshka★ 150
MCP server for token-efficient large document analysis via the use of REPL state
rekal★ 53
Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.
Comments
Log in to leave a comment
No comments yet. Be the first!