AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
ToolsCategoriesTrendingNewCompare
Home/
RAG / Knowledge Base/
codebase-memory-mcp
codebase-memory-mcp logo

codebase-memory-mcp

Active·★ 33.2k·MIT·Updated 2026-07-19
★ Hidden Gem★ RAG / Knowledge Base★ Code Assistant

codebase-memory-mcp is a structural analysis backend that indexes codebases into a persistent knowledge graph, drastically reducing token usage for code exploration by providing precise structural results. It integrates with AI assistants like Claude Code, offering advanced capabilities such as call graph tracing, architecture overviews, and dead code detection.

codebase-memory-mcp is currently grouped under RAG / Knowledge Base, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward Supports 35 programming languages: Parses source code in a wide range of languages using tree-sitter. and Code exploration and understanding: Quickly understand codebase architecture, find functions, and trace call paths without high token costs.. The listed license is MIT, which is useful when adoption constraints matter. It also shows measurable community traction with 33.2k GitHub stars.

#knowledge-graph#codebase-analysis#AI-assistant-tools#static-analysis#token-efficiency#tree-sitter#Go-lang#developer-tools
$ Install
$ codebase-memory-mcp install
↗ Visit site★ GitHub
01

Features

01Supports 35 programming languages: Parses source code in a wide range of languages using tree-sitter.
02Architecture overview: Provides instant codebase orientation by returning languages, packages, entry points, routes, and clusters.
03High token efficiency: Achieves up to 99.2% token reduction for structural queries compared to file-by-file exploration.
04Auto-sync and incremental reindex: Automatically detects file changes and triggers fast, content-hash based incremental re-indexing.
05CLI mode: Allows direct invocation of any MCP tool from the command line without an MCP client.
02

Why choose it

+Supports 35 programming languages: Parses source code in a wide range of languages using tree-sitter.
+Code exploration and understanding: Quickly understand codebase architecture, find functions, and trace call paths without high token costs.
+Covers 17 supported environments or platforms, which is helpful for broader deployment needs.
+Ships with a public repository and a MIT license, which makes adoption and review easier.
03

Trade-offs

!There are at least 8 related tools in the same category, so the best choice is easier to make after side-by-side comparison.
04

Compatibility

macOS
OS
Verified via docs
Linux
OS
Verified via docs
Windows
OS
Verified via docs
Python
Language
Verified via docs
Go
Language
Verified via docs
JavaScript
Language
Verified via docs
05

Quick start

1
$ codebase-memory-mcp install
06

Use cases

↳Code exploration and understanding: Quickly understand codebase architecture, find functions, and trace call paths without high token costs.
↳Impact analysis and refactoring: Map git diffs to affected symbols, detect dead code, and analyze function fan-out to aid refactoring efforts.
↳AI assistant integration: Enhance AI assistants like Claude Code with precise structural queries for more effective code-related questions.
↳Architecture Decision Records management: Store, update, and retrieve architectural decisions directly within the codebase context.
↳Automated scripting and CI/CD: Utilize CLI mode for single-shot graph operations in scripts or CI/CD pipelines.
07

How it compares

≈codebase-memory-mcp sits in the RAG / Knowledge Base category, so it makes more sense to evaluate it alongside tools like mindsdb instead of in isolation.
≈If your main need is closer to "Code exploration and understanding: Quickly understand codebase architecture, find functions, and trace call paths without high token costs.", that use case is a better lens for comparison than broad feature checklists alone.
≈codebase-memory-mcp uses a MIT license, and community traction are both easier to judge in category context.
08

Alternatives

mindsdb logo
mindsdb★ 39.5k
Federated Query Engine for AI - The only MCP Server you'll ever need
vs →
Brave Search MCP logo
Brave Search MCP★ 88.7k
Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.
vs →
cockpit logo
cockpit★ 13
A web UI for Claude Code that frees it from your terminal
vs →
agent-bridge logo
agent-bridge★ 247
A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。
vs →
pmb logo
pmb★ 313
Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) via MCP. 94.5% LoCoMo recall@10, 70ms p50, multilingual, zero API keys.
vs →
javalens-mcp logo
javalens-mcp★ 34
MCP server providing semantic Java code analysis for AI agents. Built on Eclipse JDT with tools for navigation, refactoring, search, and metrics.
vs →
qveris-agent-toolkit logo
qveris-agent-toolkit★ 247
Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs for agents to discover, inspect, call, and audit real-world tools.
vs →
codeindex logo
codeindex★ 268
Repo dependency analyzer with **blast-radius impact scoring** for AI-assisted development.
vs →
See all alternatives →

Related searches

codebase-memory-mcp AlternativesBest RAG / Knowledge Base Tools 2026Open Source RAG / Knowledge Basecodebase-memory-mcp Tutorialcodebase-memory-mcp Vs Competitorsknowledge-graphcodebase-analysisAI-assistant-tools

Comments

Log in to leave a comment
  • ?
    usr_seed_0775Apr 28, 2026

    Persistent knowledge graph from 35 languages of codebase indexing is impressive coverage.

  • ?
    usr_seed_0308Apr 15, 2026

    Knowledge graph structure makes code relationships discoverable, not just searchable.

  • ?
    usr_seed_0070Apr 14, 2026

    Good for polyglot projects where understanding cross-language dependencies matters.

  • ?
    usr_seed_0763Mar 20, 2026

    Persistent across sessions — the graph grows more complete over time.

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07How it compares08Alternatives
Stats
GitHub Stars★ 33.2k
Last commit2d ago
StatusActive
LicenseMIT
CategoryRAG / Knowledge Base
Trend (30d)
+1.3k↑ 2.3%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.