semble
★ 4.5k
vs
plasmate
★ 22
semble vs plasmate
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.; plasmate: Plasmate compiles HTML into a Semantic Object Model (SOM), a structured representation that LLMs can reason about directly. It runs JavaScript via V8, supports Puppeteer via CDP, and produces output that is 10-800x smaller than raw HTML. It is purpose-built for AI agent pipelines, with MCP, Vercel AI SDK integrations, and over 60 ecosystem integrations.
01
TL;DR
Choose semble if…Enhancing AI agents (e.g., Claude Code, Cursor, Codex) with fast and accurate code search capabilities
Choose plasmate if…AI agent web browsing and structured data extraction
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
plasmate01Semantic Object Model (SOM) compression: 10-800x smaller than raw HTML
02JavaScript execution via embedded V8 engine
03CDP compatibility for Puppeteer integration
04Native AWP protocol with 7 methods for agent interaction
05MCP tool server for Claude Desktop, VS Code Copilot, etc.
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
plasmate↳AI agent web browsing and structured data extraction
↳MCP tool server for LLM-based assistants (e.g., Claude Desktop)
↳Vercel AI SDK integration for agent tool calling
05
Best For
sembleCode AssistantRAG / Knowledge Base
plasmateTrendingBrowser Automation
FAQ
FAQ
What is the difference between semble and plasmate?
Both semble and plasmate are in the RAG / Knowledge Base category. semble has 4.5k stars, while plasmate has 22 stars.
Which is better, semble or plasmate?
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 plasmate if AI agent web browsing and structured data extraction.
Is semble free or open source?
Yes, semble is open source on GitHub (MIT).
Is plasmate free or open source?
Yes, plasmate is open source on GitHub (Apache-2.0).
→