AgentIndex icon
AgentIndex
semble logo
semble
★ 6.3k
vs
ken logo
ken
★ 33

semble vs ken

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.; ken: Ken is a pure Go port of semble, providing fast hybrid code search for agents with drop-in MCP compatibility. It offers a single static binary distribution, approximately 44x fewer tokens than grep+Read at recall@10, and supports indexing source code and documentation. The retrieval algorithm is a verbatim port of semble's hybrid BM25 + Model2Vec approach.

01

TL;DR

semble logo
sembleCode Assistant · ★ 6.3k

Enhancing AI agents (e.g., Claude Code, Cursor, Codex) with fast and accurate code search capabilities

Read semble full review →
ken logo
kenRAG / Knowledge Base · ★ 33

Agent code search: quickly find relevant code chunks across large codebases

Read ken full review →
02

Side-by-Side Comparison

Field
semble logosemble
ken logoken
Category
Code Assistant
RAG / Knowledge Base
Stars
★ 6.3k
★ 33
License
MIT
MIT
Install Command
pip install semble
go install github.com/townsendmerino/ken/cmd/ken@latest && go install github.com/townsendmerino/ken/cmd/ken-mcp@latest && ken download-model
Updated
1w ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agents, code-search, embeddings
agents, bm25, code-search
03

Features

semble logosemble
01Fast 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
ken logoken
01Pure Go, no cgo; single static binary with free cross-compilation
02Drop-in MCP-compatible with semble (same tool schemas and output format)
03Verbatim port of semble's hybrid BM25 + Model2Vec retrieval algorithm
04Measured ~44x fewer tokens than grep+Read at recall@10 on agent queries
05Fast cold start (~10–20ms for small indexes)
04

Use Cases

semble logosemble
↳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
ken logoken
↳Agent code search: quickly find relevant code chunks across large codebases
↳Embedded-corpus distribution: ship documentation as a single static binary with zero infrastructure
↳Database schema indexing: index live Postgres/SQLite/MySQL schemas for agent context
FAQ

FAQ

What is the difference between semble and ken?
Both semble and ken are in the Code Assistant category. semble has 6.3k stars, while ken has 33 stars.
Which is better, semble or ken?
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 ken if Agent code search: quickly find relevant code chunks across large codebases.
Is semble free or open source?
Yes, semble is open source on GitHub (MIT).
Is ken free or open source?
Yes, ken is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to semble →Alternatives to ken →semble details →ken details →