#coding-agent

Git for agent memory. Memstate gives AI agents versioned, structured memory with automatic conflict detection, full version history, and up to 80% fewer tokens than vector-based alternatives. Extracts facts from text and markdown into structured keypaths, with 84.4% accuracy on the open-source benchmark vs 20.4% for Mem0.

An experimental MCP server to use aider as a coding agent.

Reusable MCP server setup to augment AI coding agents with specific repo guidelines

DockaShell is an MCP server that gives every AI Agent its own isolated Docker container — complete with file access, shell execution, and full action traceability.

MCP server to empower your agent with enterprise-grade Gemini integration for codebase analysis, live search, text/PDF/image processing, and more on your favorite MCP clients.

Research intelligence for AI engineers. At any technical decision your team hits - agent architecture, memory, tool use, RAG, embeddings, evals, fine-tuning, distillation, MoE/inference, forecasting, vision, security, or weighing concrete tradeoffs (Mamba vs attention, LoRA vs SFT, hybrid vs dense retrieval) - Paper Lantern surfaces what 2M+ papers say in seconds, not weeks.

# 🐢🚀 Node.js Sandbox MCP ServerThis repository hosts a Node.js server that implements the Model Context Protocol (MCP) for running JavaScript in isolated Docker containers. It allows for on-the-fly npm dependency installation, making it easy to execute code safely and efficiently.

Give AI agents a visual architecture canvas — build, read, and modify system design diagrams from Claude Code, Cursor, or any MCP client.

Know what every shell command does before you approve it.

Supericons MCP lets AI coding agents search, recommend, and retrieve SVG icons from a semantic registry of 20,000+ icons. It helps builders find better icons faster inside tools like Cursor, Claude Code, Codex, Cline, and OpenCode.