tenequm/claude-kb
Universal knowledge base with Qdrant for Claude Code integration
Enables semantic search across Claude Code conversation history through Qdrant's vector database, exposing `kb_search` and `kb_get` tools via MCP server integration. Uses embeddings (configurable model, defaults to BAAI/bge-base-en-v1.5) to index messages and support similarity-based retrieval with tunable relevance scoring (0.5-0.9+ thresholds). CLI-driven workflow with Docker-based Qdrant deployment, filtering by project and optional inclusion of thinking/tool_result content.
Available on PyPI.
Stars
4
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 23, 2026
Commits (30d)
0
Dependencies
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/tenequm/claude-kb"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
giancarloerra/SocratiCode
Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local MCP:...
lyonzin/knowledge-rag
Local RAG System for Claude Code - Hybrid search (Semantic + BM25) with MCP integration
blueraai/bluera-knowledge
Local knowledge search for AI coding agents. Index repos, docs, and files with semantic +...
kantord/SeaGOAT
local-first semantic code search engine
zilliztech/deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.