Neural memory

⚠️IMPORTANT NOTICE: This is anexperimental MCP (Model Context Protocol)tool. While it has shown promising results when used locally, it is still under active development and may evolve over time.Feedback and contributions are highly appreciated!Please report any issues, suggestions, or feature requests on ourGitHub Issuespage. Your input helps make this tool better for everyone! nya~

{ "mcpServers": { "neural-memory": { "timeout": 120, "type": "stdio", "command": "npx", "args": [ "-y", "@drakonkat/neural-memory@latest" ] } } }

{ "mcpServers": { "neural-memory": { "timeout": 120, "type": "stdio", "command": "node", "args": [ "./neural-memory/src/index.js" ] } } }

⚠️Note:Replace the path with your local project path!

- No more separate databases per project!All memory resides in a single SQLite database
- Faster, simpler, zero configuration

- Rigid schemafor registering skills with consistent structure
- framework,language,filePattern,learnSteps,useCases
- Automatic context-based suggestions

- Generate visual reports of your memory
- Statistics, most used skills, recent work

import { initialize, handleMcpRequest } from 'neural-memory'; // Initialize the service await initialize(); // Add a node await handleMcpRequest('add_node', { keywords: ['fastify', 'middleware', 'auth'], content: 'Implementation of JWT middleware...', type: 'generic' }); // Register a skill await handleMcpRequest('register_skill', { name: 'Fastify CRUD API', framework: 'fastify', language: 'javascript', filePattern: '/.service.js', learnSteps: [ '1. Initialize project', '2. Create validation schema', '3. Implement handler' ], useCases: [ 'Create REST API', 'Handle standardized errors' ] }); // Search for skills const skills = await handleMcpRequest('suggest_skills', { currentKeywords: ['fastify', 'api'], domain: 'javascript' }); // Save context await handleMcpRequest('save_context_snapshot', { summary: 'Refactoring 80% complete', pendingTasks: ['Integration testing', 'Deploy to staging'], learnings: ['Prisma requires explicit migrations'] }); // Generate report const report = await handleMcpRequest('get_memory_report', { format: 'html' });

{ "name": "Skill Name", "framework": "fastify|react|prisma|...", "language": "javascript|typescript|python|...", "filePattern": "/.service.js", "learnSteps": ["Step 1", "Step 2"], "useCases": ["Case 1", "Case 2"], "implementation": "// Code...", "examples": ["file1.js"], "prerequisites": ["Prerequisite 1"] }

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Provides perfect memory for AI-assisted development by capturing project context snapshots, enabling natural language search, evolution tracking, and code intelligence.

Your AI development companion. An MCP server that gives your AI persistent memory, structured specifications, and adaptive change management — so it builds what you actually want.

A persistent development partner that prevents context drift and maintains project memory across all development sessions.

Cross-agent memory bridge with knowledge graph, workspace sync, and auto-memory hooks. Supports Windsurf, Cursor, Claude Code, Codex, and VS Code Copilot.

Thrift Memory is a cost-first MCP memory server for coding agents that stop reloading large MEMORY.md, AGENTS.md, and project context files every session. It recalls only task-relevant memory under a hard token budget and returns a savings receipt: baselineTokens vs injectedTokens vs savedTokens.

OpenMemBrain is the intelligent membrane for AI coding memory. It autonomously reads and learns from your coding sessions — you never have to tell it what to save. It selectively absorbs project knowledge, blocks secrets, filters noise, resolves conflicts, and persists only what matters.

An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .

Instead of direct calling MCP tools, mcpcode server transforms MCP tool calls into TypeScript programs, enabling smarter, lower-latency orchestration by LLMs.

Supercharge your Agent with Semantic Code Intelligence and save 💰 in the process!

AI-to-AI code review platform — Claude, Codex, and Gemini cross-check each other via MCP, REST API, and CLI for consensus-based results.