AI Agent with Architectural Memory MCP Server

@davidangularme

リポジトリ

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

davidangularme

投稿者

Fred blum

AI Agent with Architectural Memory MCP Server について

Gives any AI coding agent persistent codebase understanding. 5 tools: analyze impact (FREE), generate tests and code (PRO, 40x fewer tokens). Works with Cursor, Claude Code, VS Code, Windsurf, Cline, JetBrains.

#testing #code-analysis#architectural-memory#impact-analysis

AI Agent with Architectural Memory MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "hokmah": {
      "type": "streamable-http",
      "url": "https://hokmah.dev/mcp"
    }
  }
}

AI Agent with Architectural Memory MCP Server のツール

Analyze impact of a code change. Returns risk score, affected files, related commits. FREE — zero LLM tokens.

Generate tests from the architectural graph. 40x fewer tokens. PRO — requires API key.

Generate code with architectural memory. Reduces hallucination via graph context. PRO — requires API key.

Connect a GitHub repo to Hokmah. Builds TransitionGraph + IdeaGraph + WorldModel from commit history. FREE.

Connect an external MCP server to Hokmah for universal tool orchestration. FREE.

概要

What is AI Agent with Architectural Memory?

AI Agent with Architectural Memory (Hokmah) provides persistent codebase understanding to any AI coding agent using TransitionGraph, IdeaGraph, and WorldModel. It offers free zero‑LLM‑token impact analysis and, on the PRO plan, generates tests and code with 40× fewer tokens. Built by Catalyst AI Research, Haifa.

How to use AI Agent with Architectural Memory?

Install Hokmah and configure it to integrate with your coding environment. It works with Cursor, Claude Code, VS Code, Windsurf, Cline, and JetBrains. No specific CLI commands or config keys are documented in the README.

Key features of AI Agent with Architectural Memory

Persistent codebase understanding via TransitionGraph, IdeaGraph, and WorldModel
Zero LLM token cost for impact analysis
40× fewer tokens for test and code generation (PRO)
Compatible with Cursor, Claude Code, VS Code, Windsurf, Cline, JetBrains
Built by Catalyst AI Research, Haifa

Use cases of AI Agent with Architectural Memory

Analyze codebase impact without consuming any LLM tokens
Generate tests and code with drastically reduced token usage (PRO)
Maintain persistent architectural memory across coding sessions

よくある質問

What tools does it integrate with?

It works with Cursor, Claude Code, VS Code, Windsurf, Cline, and JetBrains.

Is there a free tier?

Yes, impact analysis is free with zero LLM tokens; test and code generation requires a PRO subscription.

What data structures does it use?

It uses TransitionGraph, IdeaGraph, and WorldModel for persistent codebase understanding.

Who built AI Agent with Architectural Memory?

It is built by Catalyst AI Research, based in Haifa.

「AI とエージェント」の他のコンテンツ

scvd.store

seancrecord

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain

Lumify Sports Intelligence

Lumify

Agent-ready sports intelligence API: live scores, odds, line movement, public betting splits, and explainable bet confidence — via 16 MCP tools at https://lumify.ai/mcp. Get a free key instantly — no signup, email, or ca

Cartesia MCP

cartesia-ai

Cartesia MCP is a remote MCP server for Cartesia (https://cartesia.ai) available at https://mcp.cartesia.ai.

fhirHydrant

faulkj

Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

Plainpaper

The AI marketing canvas for Claude and MCP agents. Your agent drafts campaigns as cards on a shared board, briefed by your brand rules, approved by you.