kerim/zotero-code-execution
Efficient multi-strategy Zotero search using code execution pattern
Implements Anthropic's code execution pattern to keep large Zotero result sets (100+ items) in the Python execution environment rather than loading into LLM context, then returns only ranked top results—eliminating crash risk and token bloat. Combines semantic, keyword, and tag-based search strategies with automatic deduplication and relevance ranking in a single `comprehensive_search()` call. Integrates with Zotero MCP and Claude Code via a skill that rewrites tool calls as local Python code execution.
Stars
38
Forks
3
Language
Python
License
MIT
Category
Last pushed
Jan 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/kerim/zotero-code-execution"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
karadHub/jenkins-ai-optimizer
Meet the beast of Jenkins MCP with AI-powered diagnostics, and more with Industrial debugging...
starkbaknet/project-vectorizer
A CLI tool that vectorizes codebases, stores them in a database, tracks changes, and serves them...
userFRM/rpg-encoder
Repository Planning Graph — semantic code understanding via MCP (arXiv:2602.02084)
houtini-ai/fanout-mcp
A Query fan-out analyser for AI Search
IronAdamant/stele-context
Local context cache for LLM agents. 100% offline, zero dependencies.