semble
★ 4.5k
vs
pubcrawl
★ 11
semble vs pubcrawl
semble: Semble is a high-performance code search library designed for AI agents, providing instant access to precise code snippets. It offers significantly faster indexing and querying compared to transformer models, achieving 99% of their retrieval quality while running entirely on CPU without external dependencies.; pubcrawl: PubCrawl is an MCP server that gives LLM clients structured access to biomedical literature databases including PubMed, FDA drug labeling, UK medicines data, and ClinicalTrials.gov. Built by PharmaTools.AI, it enables AI assistants to perform peer-reviewed literature searches, retrieve clinical trial data, and access regulatory drug information through a unified interface.
01
TL;DR
Choose semble if…Enhancing AI agents (e.g., Claude Code, Cursor, Codex) with fast and accurate code search capabilities
Choose pubcrawl if…Search and summarize biomedical literature for drug discovery and clinical research
02
Side-by-Side Comparison
03
Features
semble01Fast performance on CPU (indexes in ~250ms, queries in ~1.5ms)
02High accuracy (NDCG@10 of 0.854), comparable to transformer models
03Supports indexing local paths and remote Git repositories
04Functions as an MCP server for various AI agents
05Zero setup, no API keys, GPU, or external services required
pubcrawl01PubMed literature search with structured result parsing
02FDA drug labeling and UK medicines data retrieval
03ClinicalTrials.gov clinical trial search and data access
04Unified biomedical data interface for LLM clients
05Built for pharmaceutical and clinical research workflows
04
Use Cases
semble↳Enhancing AI agents (e.g., Claude Code, Cursor, Codex) with fast and accurate code search capabilities
↳Searching local or remote codebases for specific code snippets based on natural language or code queries
↳Finding semantically similar code sections related to a given file path and line number
pubcrawl↳Search and summarize biomedical literature for drug discovery and clinical research
↳Retrieve FDA drug labeling data for regulatory compliance and drug information workflows
↳Access clinical trial data to support evidence-based medical decision making
05
Best For
sembleCode AssistantRAG / Knowledge Base
pubcrawlHidden GemRAG / Knowledge Base
FAQ
FAQ
What is the difference between semble and pubcrawl?
Both semble and pubcrawl are in the RAG / Knowledge Base category. semble has 4.5k stars, while pubcrawl has 11 stars.
Which is better, semble or pubcrawl?
The best choice depends on your use case. Choose semble if Enhancing AI agents (e.g., Claude Code, Cursor, Codex) with fast and accurate code search capabilities, and pubcrawl if Search and summarize biomedical literature for drug discovery and clinical research.
Is semble free or open source?
Yes, semble is open source on GitHub (MIT).
Is pubcrawl free or open source?
Yes, pubcrawl is open source on GitHub (MIT).
→