AgentIndex icon
AgentIndex
ken logo
ken
★ 33
vs
coco-search logo
coco-search
★ 37

ken vs coco-search

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.; coco-search: CocoSearch is a local-first hybrid semantic code search tool that combines vector similarity and keyword matching via RRF fusion. It uses CocoIndex for indexing, Tree-sitter for syntax-aware chunking, and PostgreSQL with pgvector for storage. It supports 32 languages, 9 grammars, dependency graphs, cross-repo search, and multiple interfaces.

01

TL;DR

ken logo
kenRAG / Knowledge Base · ★ 33

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

Read ken full review →
coco-search logo
coco-searchRAG / Knowledge Base · ★ 37

Exploratory/semantic queries about code functionality

Read coco-search full review →
02

Side-by-Side Comparison

Field
ken logoken
coco-search logococo-search
Category
RAG / Knowledge Base
RAG / Knowledge Base
Stars
★ 33
★ 37
License
MIT
MIT
Install Command
go install github.com/townsendmerino/ken/cmd/ken@latest && go install github.com/townsendmerino/ken/cmd/ken-mcp@latest && ken download-model
pip install cocosearch
Updated
1d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agents, bm25, code-search
cli, cocoindex, code-explorer
03

Features

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)
coco-search logococo-search
01Hybrid search with RRF fusion
02Symbol filtering by type and name
03Syntax-aware context expansion to function/class boundaries
04Dependency graph extraction and impact analysis
05Cross-index search across multiple codebases
04

Use Cases

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
coco-search logococo-search
↳Exploratory/semantic queries about code functionality
↳Finding code by meaning rather than exact text
↳AI assistant integration for context-aware code retrieval
FAQ

FAQ

What is the difference between ken and coco-search?
Both ken and coco-search are in the RAG / Knowledge Base category. ken has 33 stars, while coco-search has 37 stars.
Which is better, ken or coco-search?
The best choice depends on your use case. Choose ken if Agent code search: quickly find relevant code chunks across large codebases, and coco-search if Exploratory/semantic queries about code functionality.
Is ken free or open source?
Yes, ken is open source on GitHub (MIT).
Is coco-search free or open source?
Yes, coco-search 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 ken →Alternatives to coco-search →ken details →coco-search details →