AgentIndex icon
AgentIndex
shokunin logo
shokunin
★ 112
vs
codesearch logo
codesearch
★ 93

shokunin vs codesearch

shokunin: Shokunin provides persistent AI memory for developers with 38 skills, multi-strategy recall (vector + BM25 + temporal), and ChromaDB memory. It is fully offline, zero server costs, and works on Windows and Linux. The system includes MCP servers, declarative self-updates, and a memory test suite.; codesearch: codesearch is a token-efficient MCP server for AI agents that enables local semantic code search. It integrates with OpenCode, Claude Code and other AI assistants to perform intelligent code searches with minimal token usage, all running locally with no external API calls.

01

TL;DR

shokunin logo
shokuninMemory & Context · ★ 112

Persistent coding context across multiple sessions

Read shokunin full review →
codesearch logo
codesearchRAG / Knowledge Base · ★ 93

AI-assisted code understanding through natural language queries

Read codesearch full review →
02

Side-by-Side Comparison

Field
shokunin logoshokunin
codesearch logocodesearch
Category
Memory & Context
RAG / Knowledge Base
Stars
★ 112
★ 93
License
MIT
Apache-2.0
Install Command
irm https://raw.githubusercontent.com/EliasOulkadi/shokunin/master/install.ps1 | iex
git clone https://github.com/flupkede/codesearch.git && cd codesearch && cargo build --release && sudo cp target/release/codesearch /usr/local/bin/
Updated
2w ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
ai-agent-skills, ai-engineering, chromadb
claude-code, code-search, embeddings
03

Features

shokunin logoshokunin
01Multi-strategy recall (vector, BM25, temporal)
02ChromaDB persistent memory across sessions
0338 domain-specific skills with procedural workflows
04MCP server support for filesystem, fetch, memory
05Fully offline, no API costs, no telemetry
codesearch logocodesearch
01Token-efficient AI integration with compact responses
02Semantic, hybrid, and neural reranking search modes
03Incremental indexing with three-layer embedding cache
04Git-aware automatic index placement and branch detection
05Privacy-first local processing with no external calls
04

Use Cases

shokunin logoshokunin
↳Persistent coding context across multiple sessions
↳Resume and continue previous development work seamlessly
↳Local AI-assisted development without cloud dependencies
codesearch logocodesearch
↳AI-assisted code understanding through natural language queries
↳Codebase navigation and reference discovery
↳Integration with AI coding assistants like OpenCode and Claude Code
FAQ

FAQ

What is the difference between shokunin and codesearch?
Both shokunin and codesearch are in the Memory & Context category. shokunin has 112 stars, while codesearch has 93 stars.
Which is better, shokunin or codesearch?
The best choice depends on your use case. Choose shokunin if Persistent coding context across multiple sessions, and codesearch if AI-assisted code understanding through natural language queries.
Is shokunin free or open source?
Yes, shokunin is open source on GitHub (MIT).
Is codesearch free or open source?
Yes, codesearch is open source on GitHub (Apache-2.0).
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 shokunin →Alternatives to codesearch →shokunin details →codesearch details →