agent-search-mcp

★ 112

claude-code-buddy

★ 16

agent-search-mcp vs claude-code-buddy

Q: Which is better, agent-search-mcp or claude-code-buddy?

By GitHub stars, agent-search-mcp has more community adoption, but the best choice depends on your specific use case.

agent-search-mcp: Agent Search MCP is an open-source, self-hosted web search router designed for AI agents, providing free, multi-source evidence with robust cost control. It supports both English and Chinese queries, offering compact output to reduce token costs for agent interactions.; claude-code-buddy: Claude Code often forgets past context and decisions, forcing developers to re-explain repeatedly. MeMesh solves this by providing Claude with persistent memory, allowing it to recall previous discussions, code setups, and project knowledge instantly.

TL;DR

agent-search-mcpRAG / Knowledge Base · ★ 112

Integrating robust web search into AI agent clients such as Claude Desktop, Cursor, or VS Code

Read agent-search-mcp full review →

claude-code-buddyRAG / Knowledge Base · ★ 16

Setting up and remembering complex authentication configurations like JWT.

Read claude-code-buddy full review →

Side-by-Side Comparison

Field

agent-search-mcp

claude-code-buddy

Features

agent-search-mcp

01Free web search with zero-key sources, eliminating the need for an API account

02Control provider costs with explicit routing policies for paid services

03Reduce token costs for LLMs through compact output and evidence budgeting

04Aggregates multi-source evidence, preserving provenance and handling partial failures

05Supports Chinese web search via Sogou and Baidu without a translation layer

claude-code-buddy

01Persistent Memory: Remembers project decisions (90 days) and session context (30 days) with semantic search capabilities.

02Knowledge Graph: Automatically organizes knowledge, links related concepts, and supports FTS5 + vector search.

03Zero Config: Auto-tracks project changes, auto-tags memories, and requires no initial configuration.

Use Cases

agent-search-mcp

↳Integrating robust web search into AI agent clients such as Claude Desktop, Cursor, or VS Code

↳Enabling AI agents to gather factual information and verify claims from multiple web sources

↳Developing agent-authored answers from cited evidence while managing token budgets effectively

↳Performing multilingual web searches, particularly for Chinese content, for various AI applications

claude-code-buddy

↳Setting up and remembering complex authentication configurations like JWT.

↳Explaining and recalling details about a codebase or architectural design decisions.

↳Troubleshooting and fixing build errors by leveraging previously stored context.

↳Recalling specific API design choices or reasons behind technology selections.

FAQ

What is the difference between agent-search-mcp and claude-code-buddy?

Both agent-search-mcp and claude-code-buddy are in the RAG / Knowledge Base category. agent-search-mcp has 112 stars, while claude-code-buddy has 16 stars.

Which is better, agent-search-mcp or claude-code-buddy?

The best choice depends on your use case. Choose agent-search-mcp if Integrating robust web search into AI agent clients such as Claude Desktop, Cursor, or VS Code, and claude-code-buddy if Setting up and remembering complex authentication configurations like JWT..

Is agent-search-mcp free or open source?

Yes, agent-search-mcp is open source on GitHub (Apache-2.0).

Is claude-code-buddy free or open source?

Yes, claude-code-buddy is open source on GitHub (AGPL-3.0).

Cloud Infrastructure

Deploy on DigitalOcean

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

Claim $200 Free Credit

→

Alternatives to agent-search-mcp →Alternatives to claude-code-buddy →agent-search-mcp details →claude-code-buddy details →

TL;DR

Side-by-Side Comparison

Features

Use Cases

FAQ

Deploy on DigitalOcean

Related