by lyonzin · MCP Server · ★ 246
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is knowledge-rag safe to install? View the security audit →
Knowledge RAG LLMs don't know your docs. Every conversation starts from zero. Your notes, writeups, internal procedures, PDFs — none of it exists to your AI assistant. Cloud RAG solutions leak your private data. Local ones require Docker, Ollama, and 15 minutes of setup before a single query. Knowledge RAG fixes this. One , zero external servers. Your documents become instantly searchable inside Claude Code — with reranking precision that actually finds what you need. 12 MCP Tools | Hybrid Search + Cross-Encoder Reranking
| Stars | 246 |
| Forks | 36 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70.9040071043056/100 |
| Open Issues | 10 |
| Last Updated | 2026-08-09 |
| Created | 2026-02-05 |
| Platforms | claude-code, cli, codex, mcp, python |
| Est. Tokens | ~25k |
Looking for a knowledge-rag alternative? If you're comparing knowledge-rag with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Agent Fusion is a local RAG semantic search engine that gives AI agents instant access to your code, documenta
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Turn local files into searchable context for AI agents.
Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google
Seline is a local-first AI desktop application that brings together conversational AI, visual generation tools
Explore other popular mcp server tools:
knowledge-rag is Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.. It is categorized as a MCP Server with 246 GitHub stars.
knowledge-rag is primarily written in Python. It covers topics such as antigravity, claude, claude-code.
You can find installation instructions and usage details in the knowledge-rag GitHub repository at github.com/lyonzin/knowledge-rag. The project has 246 stars and 36 forks, indicating an active community.
knowledge-rag is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to knowledge-rag on Agent Skills Hub include Agent-Fusion, claude-mem-lite, deepcontext-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.